Créée en 2004 par l'association ARIA (http://www.asso-aria.org/), regroupant les chercheurs francophones du domaine de la recherche d'information (RI), la conférence CORIA (Conférence en Recherche d'Information et Applications) verra sa douzième édition se dérouler du 18 au 20 Mars 2015 à Paris, France (http://coria2015.lip6.fr/).
Pendant la conférence CORIA 2015 seront également organisées les 10ièmes Rencontres Jeunes Chercheurs en Recherche d'Information (RJCRI - http://coria2015.lip6.fr/rjcri/). Elles ont pour objectif de permettre à tous les doctorants de présenter leur problématique de recherche, d?établir des contacts avec des équipes travaillant sur des domaines similaires ou connexes, et d?offrir à l?ensemble de la communauté un aperçu des axes de recherche actuels.
------------ Thématiques ------------
CORIA et RJCRI 2015 encouragent les soumissions d'articles portant sur tous les thèmes de la recherche d'information, mais aussi sur des thématiques connexes. Ces thématiques incluent, sans y être limitées :
? Théorie et modèles formels pour la RI (modèle logique, modèles probabilistes, modèles d'information, ...) ? Multilinguisme : Recherche d?information multilingue, traduction automatique ? Multimédia (images, audio, vidéos, son, musique) : indexation, navigation, accès, ... ? Passage à l?échelle : indexation, performances, architectures ? Classification automatique (y compris filtrage et routage), clustering, apprentissage automatique, ordonnancement ? Modélisation du contexte, personnalisation ? Traitement Automatique de la Langue Naturelle pour la recherche d?information ? Systèmes de Questions Réponses ? Extraction d?informations : ontologies, ressources et recherche d?informations, détection d?entités nommées et des relations ? Web : grands graphes, utilisation de la topologie du web, lois de puissances, citations, analyse de liens ? RI et documents structurés : RI et XML, RI précise et recherche de passages ? Réseaux sociaux : analyse de réseaux, de rumeurs, diffusion d'information, prédiction d'activités, ... ? Recherche collaborative : filtrage, systèmes de recommandation ? Interaction utilisateur : interrogation flexible, interfaces, visualisation, modélisation de l?utilisateur, accessibilité, indexation collaborative ? Bibliothèques numériques (RI sur des livres numérisés, reconnaissance optique de caractères) ? Systèmes de recherche d?information dédiés : recherche d?information génomique, médicale, géographique ? RI distribuée : recherche d?information mobile, située, P2P ? Outils pour la recherche d?information : évaluation, bancs d?essais, métriques, expérimentations qualitatives des systèmes
------------------------ Soumission des articles ------------------------ Les articles, soumis à CORIA et/ou à RJCRI, peuvent être rédigés en anglais ou en français. Ils doivent cependant être anonymes et ne comporter aucune mention qui pourrait permettre d'identifier les auteurs. De plus, les articles soumis ou récemment acceptés à des conférences internationales sont recevables, sous réserve qu?ils soient traduits et adaptés pour CORIA ou RJCRI.
Les contributions peuvent concerner des travaux académiques ou des applications industrielles. Les textes de communications doivent comporter 16 pages maximum pour les soumissions à CORIA, et 10 pages maximum pour les journées RJCRI. Nous acceptons les soumissions conjointes RJCRI & CORIA. Ces soumissions doivent être déposées sur les deux sites de soumission. Dans le cas d'une double acceptation, l'article sera publié au format 16 pages dans le cadre de la conférence CORIA. Dans le cas d'une acceptation seule aux RJCRI, l'article devra être réduit à 10 pages.
Les articles devront être soumis au format PDF. La première page devra être une page de garde comportant le titre de l'article, un résumé en anglais et en français, ainsi qu'une liste de mots-clés, en français et en anglais. La mention « article soumis à CORIA et RJCRI » doit être portée sur la page de garde le cas échéant. Les articles doivent respecter le format revue Hermès, dont les feuilles de style Word/Open Office et Latex peuvent être téléchargées depuis http://coria2015.lip6.fr/.
Modalités spécifiques pour les soumissions RJCRI : les auteurs doivent être EXCLUSIVEMENT des doctorant(e)s, des étudiant(e)s en Master ou de jeunes docteur(e)s ayant soutenu leur thèse depuis moins d'un an. Les soumissions pour lesquelles apparaîtront des chercheurs confirmés dans la liste des auteurs seront exclues. Les soumissions RJCRI doivent également obligatoirement être accompagnées d'une lettre du directeur de recherche (à fournir en tant que fichier attaché durant la soumission) qui devra, en particulier, indiquer si le jeune chercheur est en 1ère, 2ème ou 3ème année de thèse.
------------------------ Dates importantes ------------------------ ? Soumission des articles : 15 décembre 2014 ? Réponse aux auteurs : 26 janvier 2015 ? Dépôt des articles définitifs : 23 février 2015 ? Conférence : 18-20 mars 2015
------------------------ Comités ------------------------ Présidents des comités de programme CORIA-RJCRI ? Eric Gaussier (Université Grenoble Alpes, Grenoble, France) ? Mathias Géry (Université Jean Monnet, Saint-Etienne, France)
Présidents du comité d?organisation ? Patrick Gallinari (Université Pierre et Marie Curie, Paris, France) - Brigitte Grau (Ecole Nationale supérieure d'informatique pour l'industrie et l'entreprise, LIMSI-CNRS, Orsay, France)
Appel à participations : CORIA et RJCRI 18 au 20 mars, INSTITUT HENRI POINCARE (IHP), 11 rue Pierre et Marie Curie, 75005 Paris
Créée en 2004 par l'association ARIA (http://www.asso-aria.org/), regroupant les chercheurs francophones du domaine de la recherche d'information (RI), la conférence CORIA (Conférence en Recherche d'Information et Applications) verra sa douzième édition se dérouler du 18 au 20 Mars 2015 à Paris, France (http://coria2015.lip6.fr/).
Pendant la conférence CORIA 2015 seront également organisées les 10ièmes Rencontres Jeunes Chercheurs en Recherche d'Information (RJCRI - http://coria2015.lip6.fr/rjcri/). Elles ont pour objectif de permettre à tous les doctorants de présenter leur problématique de recherche, d?établir des contacts avec des équipes travaillant sur des domaines similaires ou connexes, et d?offrir à l?ensemble de la communauté un aperçu des axes de recherche actuels.
CORIA accueillera trois invités :
Mercredi 18 mars ? Michalis Vazirgiannis (Laboratoire d?Informatique de l?École polytechnique) Jeudi 19 mars ? Leif Azzopardi (School of Computing, Glasgow University) Vendredi 20 mars ? Peter Mika (Yahoo! Labs Barcelone)
Les inscriptions sont maintenant ouvertes.
CORIA dispose de bourses pour les doctorants et jeunes chercheurs. Les demandes doivent être faites avant le 18 février. Voir sur le site http://coria2015.lip6.fr rubrique inscription pour les informations pratiques.
------------ Thématiques de la conférence CORIA et des journées RJCRI ------------
? Théorie et modèles formels pour la RI (modèle logique, modèles probabilistes, modèles d'information, ...) ? Multilinguisme : Recherche d?information multilingue, traduction automatique ? Multimédia (images, audio, vidéos, son, musique) : indexation, navigation, accès, ... ? Passage à l?échelle : indexation, performances, architectures ? Classification automatique (y compris filtrage et routage), clustering, apprentissage automatique, ordonnancement ? Modélisation du contexte, personnalisation ? Traitement Automatique de la Langue Naturelle pour la recherche d?information ? Systèmes de Questions Réponses ? Extraction d?informations : ontologies, ressources et recherche d?informations, détection d?entités nommées et des relations ? Web : grands graphes, utilisation de la topologie du web, lois de puissances, citations, analyse de liens ? RI et documents structurés : RI et XML, RI précise et recherche de passages ? Réseaux sociaux : analyse de réseaux, de rumeurs, diffusion d'information, prédiction d'activités, ... ? Recherche collaborative : filtrage, systèmes de recommandation ? Interaction utilisateur : interrogation flexible, interfaces, visualisation, modélisation de l?utilisateur, accessibilité, indexation collaborative ? Bibliothèques numériques (RI sur des livres numérisés, reconnaissance optique de caractères) ? Systèmes de recherche d?information dédiés : recherche d?information génomique, médicale, géographique ? RI distribuée : recherche d?information mobile, située, P2P ? Outils pour la recherche d?information : évaluation, bancs d?essais, métriques, expérimentations qualitatives des systèmes
------------------------ Comités ------------------------ Présidents des comités de programme CORIA-RJCRI ? Eric Gaussier (Université Grenoble Alpes, Grenoble, France) ? Mathias Géry (Université Jean Monnet, Saint-Etienne, France)
Présidents du comité d?organisation ? Patrick Gallinari (Université Pierre et Marie Curie, Paris, France) - Brigitte Grau (Ecole Nationale supérieure d'informatique pour l'industrie et l'entreprise, LIMSI-CNRS, Orsay, France)
(2015-03-20) Conference Theory of mind and Language: Experimental data and clinical applications, Univ. Aix-Marseille, Aix-en-Provence, France
Conference Theory of mind and Language: Experimental data and clinical applications
Vendredi March 20 2015
LPL, UMR 7309 CNRS, Aix-Marseille Université Aix-en-Provence, Salle B011
Theory of mind is the ability to form representations of other people?s mental states and to use these representations to understand, predict and judge their statements and behaviours (Baron-Cohen, Leslie, & Frith, 1985; Premack & Woodruff, 1978). Study of this ability has become a major focus for cognitive sciences in the last twenty years, showing that this ability plays a fundamental role for social interactions. While loads of researches (particularly in pathology and in development) give support to a relationship between theory of mind and language, the role of this cognitive ability in meaning construction is still under debate. Is theory of mind conveyed by language (e.g. reference marker, prosody, gestures) during social interaction? Does theory of mind play a role in meaning construction? Do speakers take the perspective of the listener to explain or understand meaning? If it is the case, do linguistic forms such as reference markers or intonation contours signal how the speaker takes the listener?s perspective into account? And how do the listeners use this linguistic information to interpret the speaker?s mental states? The aim of this conference will be to present and discuss experimental data dealing with the relationship between theory of mind and language in different population (e.g. development, healthy people, pathology). Our main goal will be to bring together researchers from different backgrounds (cognitive sciences, experimental psychology, neuropsychology, psycholinguistics, phonetics/phonology, and pragmatics) with a view to improve our understanding of how language can convey theory of mind during social interactions.
The conference is organized by Maud Champagne-Lavau, Cristel Portes, Amandine Michelas (LPL) and Claire Beyssade (Paris 8 & Institut Jean Nicod)
Important dates * Deadline for abstract submission: 15 February 2015
* Notification of acceptance: 20 February 2015
* Deadline for inscription: 6 March 2015
Program
8h30 ? 9h00 : Accueil des participants / Welcome
9h00 ? 10h00 : Rethinking the Theory-of-Mind Hypothesis of Autism Tiziana Zalla, Institut Jean Nicod, CNRS UMR 8129, ENS, Paris, France
10h00 ? 10h30 : Pause/coffee break
10h30 ? 11h15 : Assessing theory of mind during conversation in Mild cognitive impairment Noémie Moreau, LPL, CNRS UMR 7309, Aix-Marseille Université
11h15 ? 12h00 : Do patients with schizophrenia use backchannels to navigate joint projects? Madelyne Klein, LPL, CNRS UMR 7309, Aix-Marseille Université
12h00-13h00 : Pause déjeuner / Lunch break
13h00 ? 14h00 : Session poster / poster session
14h00 ? 15h00 : Prosodic and referential marking in oral narratives by Adults with High Functioning Autism Francesco Cangemi1, Marion Fossard2, Martine Grice1, Martina Krüger1, Kai Vogeley3 1Institute of Linguistics, Department of Phonetics, University of Cologne, Germany. 2Institut des sciences du langage et de la communication, Université de Neuchâtel, Switzerland. 3Department of Psychiatry and Psychotherapy, University Hospital Cologne, Germany
15h00 ? 15h45 : The intonational encoding of commitment, attitude attribution and call on addressee in French Cristel Portes, LPL, CNRS UMR 7309, Aix-Marseille Université
15h45 ? 16h15 : Pause/coffee break
16h15 ? 17h00 : Relationship between theory of mind and intonational focus marking in French: Results from schizophrenia Amandine Michelas, LPL, CNRS UMR 7309, Aix-Marseille Université
17h00 ? 17h30 : Conclusion Posters Impact of sleep deprivation on sarcasm detection Gaétane Deliens, Fanny Stercq, Alison Mary, Hichem Slama, Axel Cleeremans, Philippe Peihneaux & Mikhaail Kissine Language and Social skills in Infants and Children with 22q11.2 Microdeletion Syndrome Magali Ngawa, Jean-Jacques Detraux, Koviljka Barisnikov & Steve Marejus Parent-child conversations about emotions and ToM competences in children with an Autistic Spectrum Disorder Stéphanie Mazzone & Nathalie Nader-Grosbois N400 abnormalities during intentional inference production in subjects with schizotypal traits Anne-Lise Bohec, Hélène Francisque, Alain Blanchet & Milena Kostova Theory of Mind abilities during discourse production: do elderly participants adjust their referential choices? Mélanie Sandoz, Amélie M. Achim, Jean-François Démonet & Marion Fossard A metarepresentation base approach to negation Elena Albu Liens entre théorie de l?esprit et syntaxe des complétives chez les enfants à développement typique et avec troubles du spectre autistique Morgane Burnel, Stéphanie Durrleman & Anne Reboul Cristel Portes Maître de conférences en Sciences du langage
*** Aix Marseille Université -UFR ALLSH - Pôle Langues, Langage et Cultures - Département de Sciences du langage 29 avenue Robert Schuman 13621 Aix-en-Provence Cedex 1 *** Laboratoire Parole et Langage - CNRS - UMR 7309 5 avenue Pasteur 13604 Aix en Provence 04 13 55 35 9504 13 55 35 95/ Bureau A303 http://lpl-aix.fr/person/portes
Laboratoire Parole et Langage (LPL CNRS UMR 7309, Aix-Marseille University)
Conference room B011, 5 avenue Pasteur, 13100 Aix-en-Provence, France
Theory of mind is the ability to form representations of other people’s mental states and to use these representations to understand, predict and judge their statements and behaviours (Baron-Cohen, Leslie, & Frith, 1985; Premack & Woodruff, 1978). Study of this ability has become a major focus for cognitive sciences in the last twenty years, showing that this ability plays a fundamental role for social interactions. While loads of researches (particularly in pathology and in development) give support to a relationship between theory of mind and language, the role of this cognitive ability in meaning construction is still under debate.
Is theory of mind conveyed by language (e.g. reference marker, prosody, gestures) during social interaction? Does theory of mind play a role in meaning construction? Do speakers take the perspective of the listener to explain or understand meaning? If it is the case, do linguistic forms such as reference markers or intonation contours signal how the speaker takes the listener’s perspective into account? And how do the listeners use this linguistic information to interpret the speaker’s mental states?
The aim of this conference will be to present and discuss experimental data dealing with the relationship between theory of mind and language in different population (e.g. development, healthy people, pathology). Our main goal will be to bring together researchers from different backgrounds (cognitive sciences, experimental psychology, neuropsychology, psycholinguistics, phonetics/phonology, and pragmatics) with a view to improve our understanding of how language can convey theory of mind during social interactions.
The conference is organized by Maud Champagne-Lavau, Cristel Portes, Amandine Michelas (LPL) and Claire Beyssade (Paris 8 & Institut Jean Nicod).
Registration is free but you must register to be able to attend the conference.
Call for posters
We welcome the submission of abstracts for posters on any area of scientific domains (experimental psychology, cognitive neurosciences, phonetics, phonology, pragmatics) with a view to improve our understanding of the relationship between ToM and Language.
Abstracts should be written in English or French and not exceed 250 words. An extra page may be added for figures and references. Submissions must be sent with the author’s name(s), affiliation(s) and e-mail address(es).
Important dates
Deadline for abstract submission: 15 February 2015
Notification of acceptance: 20 February 2015
Deadline for inscription: 6 March 2015
Program
8h30 – 9h00 : Accueil des participants / Welcome
9h00 – 10h00 : Rethinking the Theory-of-Mind Hypothesis of Autism
Tiziana Zalla, Institut Jean Nicod, CNRS UMR 8129, ENS, Paris, France
10h00 – 10h30 : Pause/coffee break
10h30 – 11h15 : Assessing theory of mind during conversation in Mild cognitive impairment
Noémie Moreau, LPL, CNRS UMR 7309, Aix-Marseille Université
11h15 – 12h00 : TITRE à venir
Madelyne Klein, LPL, CNRS UMR 7309, Aix-Marseille Université
12h00-13h00 : Pause déjeuner / Lunch break
13h00 – 14h00 : Session poster / poster session
14h00 – 15h00 : Prosodic and referential marking in oral narratives by Adults with High Functioning Autism
Francesco Cangemi1, Marion Fossard2, Martine Grice1, Martina Krüger1, Kai Vogeley3
1Institute of Linguistics, Department of Phonetics, University of Cologne, Germany. 2Institut des sciences du langage et de la communication, Université de Neuchâtel, Switzerland. 3Department of Psychiatry and Psychotherapy, University Hospital Cologne, Germany.
15h00 – 15h45 :The intonational encoding of commitment, attitude attribution and call on addressee in French
Cristel Portes, LPL, CNRS UMR 7309, Aix-Marseille Université
15h45 – 16h15 : Pause / coffee break
16h15 – 17h00 :Relationship between theory of mind and intonational focus marking in French: Results from schizophrenia
Amandine Michelas, LPL, CNRS UMR 7309, Aix-Marseille Université
(2015-03-27) Journées de l'ALOES: Catégories de la grammaire traditionnelle et analyse de l’oral spontané, Aix-en-Provence, France
Catégories de la grammaire traditionnelle et analyse de l’oral spontané
Vendredi 27 mars 2015 Laboratoire Parole et Langage, Aix en Provence
Ces dernières années, l’étude linguistique de la langue parlée s’est singulièrement développée, grâce notamment aux nouvelles technologies, qui facilitent de manière inestimable la collecte de données, l’analyse acoustique et les calculs statistiques. L’avancement de la recherche en pragmatique, dialectologie, analyse du discours, phonologie suprasegmentale, et d’autres encore, est considérable. Reste à savoir si la grammaire de l’anglais oral, c’est-à-dire, la connaissance des contraintes en matière d’agencement, de distribution, de combinatoire et de conditions d’emploi des termes, doit ou peut être élucidée avec les mêmes outils que celle de l’écrit.
La question que nous souhaitons poser lors de cette journée d’étude est donc : dans quelle mesure les catégories héritées des traditions grammaticales d’avant l’essor décrit plus haut sont-elles applicables à l’analyse linguistique de l’anglais oral spontané ? Par exemple, si l’on veut élucider le fonctionnement d’un réseau de marqueurs comme so, I mean, that is, qui peuvent paraître sémantiquement proches ou interchangeables dans certains contextes, est-il utile de savoir qu’ils proviennent de constructions hétérogènes (adverbe de phrase, proposition à sujet personnel ou impersonnel) ? Y aurait-il un terme apte à les regrouper, ou faudrait-il se contenter de « discourse markers », qui rassemble tellement d’entités que sa valeur explicative est faible ?
Par catégorie, on n’entend pas seulement parties du discours et types de phrases mais aussi des notions telles que subordination, hypothétique, parenthétique, discours direct et indirect, portée, etc …
Face à des passages d’oral spontané, plusieurs entrées sont possibles pour traiter de cette problématique:
par marqueurs ou jeux de marqueurs (ex : I mean, you know : combinaison, alternance, interchangeabilité…)
par schéma intonatif et/ou accentuel (ex : ton descendant sur une syntaxe non déclarative…)
par catégories grammaticales (ex : sorta (of), wanna (to), coulda (have) :un marqueur ou plusieurs ?)
Les communicants sont invités à choisir un corpus d’oral spontané, en diffusant des passages sonores de préférence dialogués, ce qui exclut le recours à des textes transcrits sans support oral ainsi qu’à de l’écrit oralisé (discours journalistique et discours préparé).
Les propositions de communication (25 minutes) devront être envoyées pour le 15 janvier 2015 à Isabelle Gaudy-Campbell (isabelle.gaudy-campbell@univ-lorraine.fr). Elles comprendront une vingtaine de lignes et seront accompagnées d’une courte bibliographie. Les langues de travail sont le français et l'anglais. Une notification d’acceptation sera adressée dans les 15 jours.
La journée d’étude se tiendra la veille de la journée de l’ALOES au Laboratoire Parole et Langage, 5 avenue Pasteur, 13100 Aix en Provence.
*OSLiA (Oral Spontané et Linguistique Anglaise) est un réseau qui compte parmi les Special Interest Groups de l’ALOES.
(2015-04-20) Mobile Voice Conference, San Jose, CA, USA
'Relationships with Personal Assistants, from the Assistants' Point of View'
Rob Chambers, the Group Engineering Manager for the Audio and Speech Platform team at Microsoft, will deliver a keynote talk, 'Relationships with Personal Assistants, from the Assistants' Point of View.' Chambers asks, Have you ever wondered what it?s like to be a ?digital? personal assistant? What about answering the questions of millions of people all at the same time, across all different languages? In this keynote session, Rob Chambers will present what he believes the industry?s leading digital personal assistants currently think about their roles, the challenges that they face, and the steps that they?re taking to become the best digital personal assistants for each and every one of their users.
Chambers is responsible for integrating speech and natural language into Windows 10. Previously, Rob managed the delivery of all cloud-based systems that power Cortana, Microsoft?s personal digital assistant. Rob has spent the majority of his 20 years at Microsoft driving the advance of speech and natural language across a wide spectrum of Microsoft products.
The Mobile Voice Conference is being held in San Jose, California, April 20-21. Check out the full program.
The Mobile Voice Conference is organized by the Applied Voice Input Output Society (www.AVIOS.org) and Bill Meisel's TMA Associates (www.tmaa.com), publisher of Speech Strategy News.
For information on sponsorship opportunities, contact info@mobilevoiceconference.com
Share OnlineLike on Facebook Tweet this on Twitter?
AVIOS 1458 Athenour Ct. San Jose California 95120 United States
(2015-05-07) 3rd International Conference on Learning Representations (ICLR2015), San Diego, USA
------------------------------------------------------------------- 3rd International Conference on Learning Representations (ICLR2015) -------------------------------------------------------------------
Website: http://www.iclr.cc/ Submission deadline: December 19, 2014 Location: Hilton San Diego Resort & Spa, May 7-9, 2015
Overview -------- It is well understood that the performance of machine learning methods is heavily dependent on the choice of data representation (or features) on which they are applied. The rapidly developing field of representation learning is concerned with questions surrounding how we can best learn meaningful and useful representations of data. We take a broad view of the field, and include in it topics such as deep learning and feature learning, metric learning, kernel learning, compositional models, non-linear structured prediction, and issues regarding non-convex optimization.
Despite the importance of representation learning to machine learning and to application areas such as vision, speech, audio and NLP, there was no venue for researchers who share a common interest in this topic. The goal of ICLR has been to help fill this void.
A non-exhaustive list of relevant topics: - unsupervised, semisupervised, and supervised representation learning - metric learning and kernel learning - dimensionality expansion - sparse modeling - hierarchical models - optimization for representation learning - learning representations of outputs or states - implementation issues, parallelization, software platforms, hardware - applications in vision, audio, speech, natural language processing, robotics, neuroscience, or any other field
The program will include keynote presentations from invited speakers, oral presentations, and posters. This year, the program will also include a joint session with AISTATS.
ICLR's Two Tracks ----------------- ICLR has two publication tracks.
Conference Track: These papers are reviewed as standard conference papers. Papers should be between 6-9 pages in length. Accepted papers will be presented at the main conference as either an oral or poster presentation and will be included in the official proceedings. A subset of accepted conference track papers will be selected to participate in a JMLR special topics issue on the subject of Representation Learning. Authors of the selected papers will be given an opportunity to extend their original submissions with supplementary material.
Workshop Track: Papers submitted to this track are ideally 2-3 pages long and describe late-breaking developments. This track is meant to carry on the tradition of the former Snowbird Learning Workshop. These papers are non-archival workshop papers, and therefore may be published elsewhere.
Note that submitted conference track papers that are not accepted to the conference proceedings are automatically considered for the workshop track.
ICLR Submission Instructions ---------------------------- 1. Authors should post their submissions (both conference and workshop tracks) on arXiv: http://arxiv.org 2. Once the arXiv paper is publicly visible (there can be an approx. 30 hour delay), authors should go to the openreview ICLR2015 website to submit to either the conference track or the workshop track.
To register on the openreview ICLR2015 website, the submitting author must have a Google account.
Notes: i. Regarding the conference submission's 6-9 page limits, these are really meant as guidelines and will not be strictly enforced. For example, figures should not be shrunk to illegible size to fit within the page limit. However, in order to ensure a reasonable workload for our reviewers, papers that go beyond the 9 pages should be formatted to include a 9 page submission and a separate supplementary material submission that will be optionally reviewed. If the paper is selected for the JMLR special topic issue, this supplementary material can be incorporated into the final journal version. ii. Workshop track submissions should be formatted as a short paper, with introduction, problem statement, brief explanation of solution, figure(s) and references. They should not merely be abstracts. iii. Paper revisions will be permitted, and in fact are encouraged, in response to comments from and discussions with the reviewers (see 'An Open Reviewing Paradigm' below). iv. Authors are encouraged to post their papers to arXiv early enough that the paper has an arXiv number and URL by the submission deadline of 19 Dec. 2014. However, if these are not yet available, authors have up to one week after the submission deadline to provide the arXiv number and URL. At submission time, simply provide the title, authors, abstract, and temporary arXiv number indicating that the paper has been submitted to arXiv.
An Open Reviewing Paradigm -------------------------- 1. Submissions to ICLR are posted on arXiv prior to being submitted to the conference. 2. Authors submit their paper to either the ICLR conference track or workshop track via the the openreview ICLR2015 website. 3. After the authors have submitted their papers via openreview.net, the ICLR program committee designates anonymous reviewers as usual. 4. The submitted reviews are published without the name of the reviewer, but with an indication that they are the designated reviews. 5. Anyone can openly (non-anonymously) write and publish comments on the paper. Anyone can ask the program chairs for permission to become an anonymous designated reviewer (open bidding). The program chairs have ultimate control over the publication of each anonymous review. Open commenters will have to use their real names, linked with their Google Scholar profiles. 6. Authors can post comments in response to reviews and comments. They can revise the paper as many times as they want, possibly citing some of the reviews. Reviewers are expected to revise their reviews in light of paper revisions. 7. The review calendar includes a generous amount of time for discussion between the authors, anonymous reviewers, and open commentators. The goal is to improve the quality of the final submissions. 8. The ICLR program committee will consider all submitted papers, comments, and reviews and will decide which papers are to be presented in the conference track, which are to be presented in the workshop track, and which will not appear at ICLR. 9. Papers that are presented in the workshop track or are not accepted will be considered non-archival, and may be submitted elsewhere (modified or not), although the ICLR site will maintain the reviews, the comments, and the links to the arXiv versions.
General Chairs -------------- Yoshua Bengio, Université de Montreal Yann LeCun, New York University and Facebook
Program Chairs -------------- Brian Kingsbury, IBM Research Samy Bengio, Google Nando de Freitas, University of Oxford Hugo Larochelle, Université de Sherbrooke
Contact ------- The organizers can be contacted at iclr2015.programchairs@gmail.com
The doctoral students in Linguistics of the laboratories at Toulouse University, France:
CLLE-ERSS (Équipe de Recherche en Syntaxe et Sémantique)
IRIT (Institut de Recherche en Informatique de Toulouse)
OCTOGONE-Lordat (Centre Interdisciplinaire des Sciences du Langage et de la Cognition)
are organizing the 5th edition of JéTou (Journées d'études Toulousaines), an international conference aiming at gathering doctoral students and young researchers (who have defended their dissertation within the past three years) together, from the different disciplines of Linguistics, on an open and multidisciplinary theme.
This 2015 edition will be devoted to a reflection on the following theme: “Discourse(s) in Linguistics: Units and Levels of Analysis”.
The term discourse, understood in its broadest sense as a multimodal language production (oral, written, verbal, gestural) is at the heart of Linguistics. Both in production and reception, investigation methods have led to analysis levels with variable granularities, where overlapping units maintain relationships with strong interdependence. Therefore, discourse depends on both the object and the meaning given to it.
Common issues are: planning, segmentation, organization, modeling. A valuable reflection involving different fields arises from these challenges; more than ever, an interdisciplinary practice is necessary to further the various aspects of discourse.
Research in these fields has taken different forms. Besides, the gap between theoretical models and empirical studies based on real data has been significantly reduced in the last few years. Qualitative as well as quantitative, these works have raised new questions: choice of units, collection and annotation of corpora, evaluation procedures, comparison and interpretation of results, etc.
This edition will focus mainly on levels of analysis and units in discourse. Possible topics include:
Phonetics and Phonology:availability and authenticity of oral corpora, phonetic and phonological features of discourse (monolingual or bilingual) in perception and production.
Psycholinguistics and Neurolinguistics:pathological speech, bilingual speech, planning, organizing, processing, development and cognitive aging.
Acquisition and Learning of Languages:mutual contributions between the study of discourse and learning L1 and L2, interference.
Natural Language Processing:parsing rhetoric, synthesis and speech recognition, information extraction, importance of discourse in local use (morpho-syntactic tagging, named entity recognition).
Obviously, this list does not include all the research possibilities following from the theme of the conference, which is why every submission that addresses the notions of discourse in the Language Sciences will be read and reviewed. Proposals which include theoretical reflections and actual data will be particularly appreciated.
JéTou 2015 offers a challenging theme that every field of Language Sciences can adapt for themselves. This conference will give the opportunity, to those who wish to come, to ask questions, discuss and compare their work, their methods, their reflections in an interdisciplinary context, which favours positive interactions and constructive debates.
Guest Speakers :
Nicholas Asher, IRIT, Université Paul Sabatier (Toulouse, France)
Anne-Catherine Simon, Valibel, Université catholique de Louvain (Louvain-laNeuve, Belgium)
Submission Guidelines:
Articles must be written in French or English.
Submissions must not exceed 3 pages for an oral presentation as well as for a scientific poster (references included). These three pages must include a title, a summary and up to 5 keywords (letter type: Times New Roman 12, simple spacing, normal margin). You can indicate by email your preference for an oral presentation (20 min + 10 min for questions) or for a scientific poster, but the final decision on the format of the presentation will be made by the organization committee alone.
Papers should be submitted via the EasyChair conference system:
Workshop in Lexicography, Corpus Linguistics and Lexical Computing
Tel?, Czech Republic
June 8th-12th 2015
Lexicom is a five-day intensive workshop created by the Lexicography MasterClass. Seminars on theoretical issues alternate with hands-on work at the computer. Working in small groups or individually, you will learn how to create dictionaries and other lexical resources, from the preparation of corpora to the planning, design and writing of entries. This is the workshop's fifteenth year and we now have over 380 graduates, from all parts of the world: reviews of previous events can be found here. It will be led by Michael Rundell, Milo? Jakubí?ek, Adam Kilgarriff and Vojt?ch Ková? For more details and registration form see http://www.lexmasterclass.com/lexicom-telc-2015/
(2015-06-10) 13th International Workshop on Content-Based Multimedia Indexing, Prague, Czech Republic (Extended deadline)
CBMI 2015 13th International Workshop on Content-Based Multimedia Indexing June 10.-12. 2015, Prague, Czech Republic http://siret.ms.mff.cuni.cz/cbmi2015/
*** Call for papers and demos ***
?Full paper submission deadline: March 22, 2015 ?Demo paper submission deadline: March 7, 2015 ?Special session on Medical Multimedia Processing submission deadline: March 7, 2015 ?Special session on High Performance Multimedia Indexing submission deadline: March 7, 2015
Following the twelve successful previous events of CBMI (Toulouse 1999, Brescia 2001, Rennes 2003, Riga 2005, Bordeaux 2007, London 2008, Chania 2009, Grenoble 2010, Madrid 2011, Annecy 2012, Veszprem 2013, and Klagenfurt 2014), it is our pleasure to welcome you to CBMI 2015, the 13th International Content Based Multimedia Indexing Workshop, in Prague, Czech Republic on June 10-12 2015.
The 13th International CBMI Workshop aims at bringing together the various communities involved in all aspects of content-based multimedia indexing, retrieval, browsing and presentation. The scientific program of CBMI 2015 will include invited keynote talks and regular, special and demo sessions with contributed research papers.
================================================== * Special session on Medical Multimedia Processing
A special session on Medical Multimedia Processing will be organized. Topics of the special session include, but are not limited to: ? Visual indexing of medical image collections or video archives ? Medical multimedia retrieval ? Browsing and presentation of medical multimedia data ? Endoscopic video processing ? Human computation for medical multimedia processing
========================================================= * Special session on High Performance Multimedia Indexing
A special session on High Performance Multimedia Indexing will be organized. Topics of the special session include, but are not limited to: ? Vectorized algorithms for multimedia indexing ? GPU and many-core implementations of multimedia indexing ? Cache-aware and cache-oblivious algorithms for content-based multimedia retrieval ? Parallel and NUMA-aware algorithms for multimedia indexing ? Distributed and heterogeneous implementations of multimedia indexing algorithms
Depuis peu, on voit émerger un intérêt réciproque entre des sous-disciplines des Sciences du langage qui n’avaient guère coutume de dialoguer : la présente rencontre, qui réunit analystes du discours, phonéticiens, sémanticiens, didacticiens, acquisitionnistes, historiens de la langue et des représentations linguistiques, sociologues du langage etc. en est une illustration. Ce choc des cultures amène l’analyse du discours à considérer des discours oraux, écrits, hybrides sortant de « l’ordinaire », à s’ouvrir à une analyse de discours qui, envisagés depuis les traditions disciplinaires de l’AD et du point de vue de leurs fonctionnements ou encore des présupposés épistémologiques qu’ils interrogent ou bousculent, peuvent être qualifiés de hors-normes.
Les domaines d’études où le hors-norme se manifeste ne sont pas limités aux points listés ci-dessous, toute proposition pertinente sera étudiée avec attention.
Discours analysés dans le domaine de la littératie
Très peu d’études convoquent l’analyse de discours dans les études de littératie, bien qu’elle se révèle particulièrement intéressante pour examiner les rapports exprimés à la lecture/écriture, les productions en tant que telles ainsi que les discours publics sur les questions de littératie. De nombreux paramètres sont à prendre en considération si l’on considère la littératie selon une acception socio-culturelle (New Litteracy Studies) : rapports de pouvoir entre certaines littératies (pratiques hors-normes) et discours dominants (y compris langue commune) ; descriptions sociales et discursives de pratiques innovantes (le parlécrit (Jeay,1991) des textes/SMS) ; parcours interprétatifs imprévus, décalés en contexte de réception : quelles marges discursives pour l’interprétation hors-norme ? On accordera une attention particulière à l’historicité des normes linguistiques. L’accès à la lecture et à l’écriture a une histoire : comment, dans ses différents moments, sa gradualité a-t-elle été appréhendée ? On interrogera l’espace discursif qu’occupent ceux que l’on a pu nommer ici peu-lettrés, ailleurs semicolti, ou encore situer dans le clair-obscur du « substandard ».
Discours analysés dans le domaine des situations de travail, de la vie socio-professionnelle, des politiques sociales, de l’emploi, du travail social
Cadrés par de nombreuses injonctions politiques et par des discours prescriptifs, les univers organisés sont des lieux de fabrication et de circulation de normes. Lorsqu’elles sont mises en débat, celles-ci n’induisent-elles que de la légitimation ou de la contestation ? Des discours porteurs de « logiques autres », de rationalités hétérogènes, alternatives, voire dissidentes sont-ils développés ? Le hors-norme exprime-t-il un discours de résistance ? de refus ? de retrait ? de débrouille pour échapper aux contraintes du travail ou des politiques publiques ? Quelles sont ses propriétés (inter)discursives, énonciatives, argumentatives ?
Discours analysés dans le domaine de la pathologie du langage, ou des pathologies censées affecter le langage
Quel rôle jouent, dans la perception du hors norme, le « référent interne » (Fex, 1992), la variabilité des canons esthétiques, l’attitude des soignants et aidants ? Quelle correspondance entre cette perception et la description des discours produits ? Quels paramètres (articulatoires, acoustiques, linguistiques,…) caractérisent un discours pathologique par rapport à un discours dit « normal » ? La notion d’art brut a ouvert une approche de certaines de ces productions en tant que phénomènes de création (Adam, 2012), l’AD peut-elle proposer d’autres pistes ?
Discours analysés dans le domaine des études de l’oralité
Quels ratés de la communication orale, quels dérapages, glissements involontaires qui produisent des équivoques, des lapsus et malentendus ? Quels énoncés constituent les chutes des corpus oraux, les énoncés délaissés, faute de catégories analytiques adéquates ? En quoi certains énoncés ou bribes d’énoncés oraux sortent-ils des cadres d’analyse prévisibles ? Pourquoi ces énoncés semblent-ils défier les outils notionnels et méthodologiques de l’analyste ?
Discours analysés dans le domaine de l’acquisition du langage
Le discours de l’enfant, de l’apprenant s’inscrit dans un processus. Par nature « hors-normes », il est pourtant observé en référence à des stades de développement, constituant une forme de norme. Pour comprendre comment s’opèrent perception et signalement du hors-norme, on s’interrogera notamment sur les notions de (hors)-norme scolaire tel qu’il est formulé dans les discours institutionnels et sociaux, sur les attitudes socio-discursives des parents, éducateurs et enseignants.
Sous quelles formes, quels contenus et selon quelles conditions de production, les discours sociaux recourent-ils au hors-norme ? Selon quels paramètres sociaux et discursifs les locuteurs placent-ils le curseur entre norme et hors-norme ? En interrogeant la qualification de « hors-norme » appliquée à des discours, ce colloque invite aussi à repenser les normes de l’analyse de discours.
Éléments de bibliographie
Adam, Jean-Michel, 2012, Préface de Ecrivainer. La Langue morcelée de Samuel Daiber, par Vincent Capt, Lausanne, Infolio Collection de l’Art Brut, Collection Contre-courant.
Angenot, Marc,2008, Dialogues de sourds. Traité de rhétorique antilogique, Paris, Mille et une nuit, collection Essais.
Bourdieu, Pierre, 1983 « Vous avez dit 'populaire' ? », Actes de la recherche en sciences sociales, Vol. 46, L’usage de la parole, p. 98-105.
Branca-Rosoff, Sonia, Schneider, Nathalie, 1994, L’écriture des citoyens. Une analyse linguistique de l'écriture des peu-lettrés pendant la période révolutionnaire, Paris, Klincksieck.
Bres, Jacques, Haillet, Patrick-Pierre, Mellet, Sylvie, Nolke, Henning, Rosier, Laurence (éds), 2005, Dialogisme et polyphonie, Bruxelles, De Boeck.
Collette, Karine, Rousseau, Jean, 2013, « Littératie et responsabilité en santé », Globe, revue internationale d’études québécoises, vol.16, no 1, p. 133-157.
De Robillard, Didier, 2008, Perspectives alterlinguistiques, Paris, L’Harmattan, vol. 1 et 2.
Demonet Michel, Geffroy Annie, Gouaze Jean, Lafon Pierrre, Mouillaud, Maurice, Tournier, Maurice, 1978 [1975], Des tracts en Mai 68. Mesures de vocabulaire et de contenu, Paris, Champ libre (1re édition : Presses de la FNSP).
Didirkova, Ivana, Hirsch, Fabrice, 2014, « Etude préliminaire des caractéristiques phonétiques sur le bégaiement : le cas du français et du slovaque », Actes des XXXe Journées d'Etudes sur la Parole, Le Mans, 23-27 juin, http://www-lium.univ-lemans.fr/jep2014/articles/20.pdf.
Ernst Gerhard, 2003, « Les peu lettrés devant les normes de la textualité », D. Osthus, C. Polzin-Haumann, C. Schmitt (éds), La norme linguistique, Bonn, Romanistischer Verlag.
Ernst, Gerhard, 2010, « “qu’il n’y a orthographe ny virgule encorre moins devoielle deconsol et pleinne delacunne“ : la norme des personnes peu lettrées (XVIIe et XVIIIe siècles) », M. Iliescu, H. Siller-Runggaldier, P. Danler (éds), Actes du XXVe Congrès International de Linguistique et de Philologie Romanes, Innsbruck 2007, Berlin, New York, De Gruyter, vol. 3, p. 543-551.
Fairon, Cédric, Cougnon, Louise-Amélie, 2014, SMS Communication. A Linguistic Approach, Amsterdam/Philadelphia, John Benjamins.
Fex Sören, « Perceptual evaluation », Journal of Voice, 1992, 6, p. 155-158.
Foucault, Michel, 1973, Moi, Pierre Rivière ayant égorgé ma mère, ma sœur et mon frère : un cas de parricide au XIX e siècle, Paris, Gallimard. Gadet, Françoise, Pêcheux, Michel, 1998, La langue introuvable, Paris, Maspero. Jeay, Anne-Marie, Les messageries télématiques, Paris, Eyrolles, 1991.
Larrivée, Pierre, 2011, « Au-delà de la polyphonie », Le Français moderne, 79, 1, p.223-234.
Macherey, Pierre, 2009, De Canguilhem à Foucault. La force des normes, Paris, La Fabrique.
Maingueneau, Dominique, 2014, Discours et analyse de discours, Paris, Armand Colin.
Manesse, Danièle, « Les enfants des classes populaires, la langue et la norme », Cahiers pédagogiques, 500, p. 92-94.
Paveau, Marie-Anne, 2010, « La norme dialogique. Propositions critiques en philosophie du discours », Semen, n° 19, p. 141-159.
Pêcheux, Michel, 1969, L’analyse automatique du discours, Paris, Dunod.
Ricoeur, Paul, 1986, l’idéologie et l’utopie, Paris, Seuil, 1997.
Sarfati, Georges-Élia, 2008, « Pragmatique linguistique et normativité : remarque sur les modalités discursives du sens commun », Langages vol. 2, 170, p. 92-108.
Siouffi, Gilles, Steuckardt, Agnès (éds), 2007, Les linguistes et la norme, Berne, Peter Lang. Tournier, Maurice, 2002, Propos d’étymologie sociale 1, 2 et 3, Lyon, ENS Éditions.
NLDB 2015 invites researchers from academia and industry to submit papers for oral or poster presentations on recent, unpublished research that addresses theoretical aspects, algorithms, applications, architectures for applied and integrated NLP, resources for applied NLP, and other aspects of NLP, as well as survey and discussion papers.
Special Track: Semantic and Cognitive Computing ----------------------------------------------- For the 20th edition of NLDB, we especially solicit submissions for our special track: Natural Language and its connection to Semantic and Cognitive Computing. Semantic computing aims at connecting the meaning of the user?s need with semantics of content in a multidisciplinary fashion. Cognitive Computing systems naturally interact with people and learn over time. While natural language understanding is necessary for semantic understanding and interacting with a cognitive system (e.g. a question answering system or a search application), it is an open question how to leverage direct or indirect user feedback for improving the overall system's output, but also for improving the natural language processing stack and evolving the system's knowledge representations. Further, the interaction of natural language and formalized knowledge repositories is attained differently in the literature. Papers for the special track especially focus on the adaptivity and the combination of NL and knowledge processing systems: domain adaptation, adaptation over time, adaptivity and user feedback, wisdom of the crowds, information fusion from heterogeneous sources, incremental/online machine learning. We especially encourage submission of survey and discussion papers for the special track.
NLDB'15 Topics -------------- Further, we encourage submissions on the following topics:
* Applications of NLP in Information Systems: Multilingual Information Systems, NLP in Requirement Engineering, NLP in Knowledge Management, Semantic Data Integration and Data Cleaning.
* Social Media and Web Data: Corpus analysis, Language identification, Text normalization, Robust NLP for social media, Text classification, Information Extraction and Sentiment Analysis for social media.
* Semantic Web Open Linked Data: Ontology Learning and Alignment, Populating ontologies, Querying Ontologies and linked data, Semantic tagging and classification, Ontology-driven NLP.
* Question Answering (QA): NL interfaces to databases, QA using web data, multi-lingual QA, Non-factoid QA (how/why/opinion questions, lists), geographical QA, QA corpora and training sets.
* Natural language and Ubiquitous Computing: Pervasive Computing, Embedded, Robotic and Mobile Applications.
* Natural Language in Conceptual Modeling: Analysis of Natural Language Descriptions, Terminological Ontologies, Consistency Checking, Metadata Creation and Harvesting, Ontology-driven Systems Integration, Ontology Management.
* NLP Applications: Business Intelligence, Subjectivity and Sentiment Analysis, QA systems, Event Detection, Named Entity and Event Detection, Information Extraction, Summarization, NLP for Data Mining, NLP for Data Warehouses, Plagiarism detection, Identity detection.
Submission information ---------------------- All accepted papers will be included in Springer proceedings of the conference. We solicit four types of papers: * Long papers: Up to 12 pages, plus references. Long papers should describe unpublished, complete research * Short papers: Up to 6 pages, plus references. Short papers describe a comparative evaluation of existing works, a negative result, or consist of a survey, discussion or position paper. * Poster and Demo papers: Up to 4 pages, plus references: Poster/Demo papers describe a small focused result, a negative result, or a late-breaking result, or a description of a system that can be demonstrated on-site at the conference.
Organization ------------ Siegfried Handschuh, University of Passau, Germany (Conference Chair) Elisabeth Métais, CNAM, France (Conference Chair) Farid Meziane, University of Salford, UK (Conference Chair) Chris Biemann, TU Darmstadt, Germany (Program Chair) André Freitas, University of Passau, Germany / Insight, Ireland (Local Organisation Chair)
Senior Programme Committee ????????????? Gerard de Melo, Tsinghua University, China Valia Kordoni, HU Berlin, Germany Mathieu Lafourcade, LIRMM, France Johannes Leveling, CNGL, Dublin City University, Ireland Els Lefever, Ghent University, Belgium Simone Paolo Ponzetto, University of Mannheim, Germany Mathieu Roche, Cirad, TETIS, France Maguelonne Teisseire, Irstea, TETIS, France Christina Unger, CITEC, Universität Bielefeld, Germany Torsten Zesch, University of Duisburg-Essen, Germany Michael Zock, CNRS-LIF, France
Important Dates --------------- January 31, 2015: Deadline for paper submission March 15, 2015: Notifications March 31, 2015: Final versions due June 17-19, 2015: Conference in Passau, Germany
(2015-06-22) 22nd conference on Natural Language Processing, Caen, France,
TALN 2015 Conference Call for Workshops ----------------
22nd conference on Natural Language Processing University of Caen Lower Normandy June 22-25, 2015 - Caen, France http://taln2015.greyc.fr
---------------- GOALS ----------------
Workshops are aimed at specific TALN themes in order to gather targeted presentations. Each workshop has its own program committee and president. Each workshop organizer is in charge of the workshop call for papers and paper selection. The TALN conference committee will make take care of the local arrangements and organization (conference rooms, breaks and paper publication).
---------------- IMPORTANT DATES ----------------
-Workshop submission deadline: Friday, January 30, 2015 (23:59 Paris time) -Program Committee response: Friday, February 6 2015 -Camera ready paper due: Friday, May 8, 2015
Workshop proposals should be sent via email to Jean-Marc Lecarpentier (jean-marc.lecarpentier[at]unicaen.fr). Proposals should include a brief description of the theme and goals of the workshop (1 page in PDF), the composition of the program committee and the wished length of the workshop. The TALN program committee will select workshops amongst the proposals received.
---------------- FORMAT ----------------
Workshop papers are in French (or in English for authors not speaking French). Workshop papers must adhere to the TALN style and are between 12 and 14 pages.
Nous sommes heureux d'annoncer la tenue du premier atelier ETeRNAL, qui se tiendra pendant la conférence TALN 2015, à Caen.
Le Traitement Automatique des Langues (TAL) est une discipline au coeur des enjeux éthiques du XXIe siècle : accès aux données personnelles et protection de la vie privée, traitement (et croisement) des masses de données, délocalisation et crowdsourcing (myriadisation) sont autant de problématiques qui sont en lien direct avec les applications que nous développons.
Les questions sous-jacentes que nous souhaitons voir aborder concernent aussi bien les apports du TAL à l?éthique que nos responsabilités en tant que producteurs d?outils. Nous ne pouvons en effet pas faire semblant de ne pas savoir que ceux-ci rendent possibles des abus, des actes criminels, des violations des droits individuels. Aujourd?hui, de quoi les outils de TAL sont capables ? Jusqu?où s?étend notre responsabilité morale ? Devons- nous être des lanceurs d?alertes ? Quels mesures peut-on prendre pour limiter les effets potentiellement négatifs de nos recherche ?
Thèmes abordés
données sensibles myriadisation (crowdsourcing) et éthique questions éthiques autour de l?utilisation des outils ou du résultat des traitement qualité et biais de l?évaluation aspects juridiques, économiques TAL pour l?éthique (dont anonymisation)
Dates importantes
Date limite de soumission : 5 avril 2015 Notification aux auteurs : 4 mai 2015 Date limite de soumission des versions définitives : 22 mai 2015 Atelier : 22 juin 2015
Soumission des articles
Les articles seront rédigés en français pour les francophones, en anglais pour ceux qui ne maîtrisent pas le français. Ils devront suivre le format de TALN-RÉCITAL 2015 et comprendront un maximum de 12 pages. Une feuille de style LaTeX et un modèle MS Word et OpenOffice sont disponibles sur le site web de la conférence TALN 2015 (https://taln2015.greyc.fr/soumissionstaln/). Les articles acceptés donneront lieu à une présentation au cours de l'atelier. Les critères de sélection sont les mêmes que ceux définis par TALN 2015 pour les articles de recherche.
Gilles Adda, IMMI / LIMSI-CNRS Maxime Amblard, Université de Lorraine / LORIA Karën Fort, Université Paris 4 / STIH
Comité scientifique
Gilles Adda, IMMI / LIMSI-CNRS Maxime Amblard, LORIA Université de Lorraine Olivier Baude, LLL / Université d?Orléans Philippe Blache, LPL CNRS Kevin Bretonnel Cohen, University of Colorado School of Medicine Gaël de Chalendar, CEA LIST Alain Couillault, Université de La Rochelle / L3i Cécile Fabre, Université Toulouse 2 / CLLE-ERSS Karën Fort, Université Paris 4 / STIH Cyril Grouin, LIMSI-CNRS Joseph Mariani, IMMI / LIMSI-CNRS Adeline Nazarenko, Université Paris 13 / LIPN - CNRS Michel Simard, NRC-CNRC Isabelle Tellier, Université Paris 3 / LaTTice
Contact : Karën Fort (karen.fort@paris-sorbonne.fr)
TALN Long paper (10 to 12 pages) -Paper submission deadline: Friday, January 30, 2015 (23:59 Paris time) -Notification: Monday, March 30, 2015 -Camera ready paper due: Friday, May 8, 2015
TALN Short paper (4 to 6 pages) -Paper submission deadline: Friday, April 3, 2015 (23:59 Paris time) -Notification: Wednesday, May 13, 2015 -Camera ready paper due: Friday, May 22, 2015
TALN Demonstration (1 to 2 pages) -Submission deadline: Friday, May 8, 2015 (23:59 Paris time) -Notification: Friday, May 15, 2015 -Camera ready paper due: Friday, May 22, 2015
RÉCITAL paper (10 to 12 pages) -Paper submission deadline: Friday, March 20, 2015 (23:59 Paris time) -Notification: Tuesday, April 28, 2015 -Camera ready paper due: Friday, May 15, 2015
Workshop proposal -Workshop submission deadline: Friday, January 30, 2015 (23:59 Paris time) -Program Committee response: Friday, February 6, 2015 -Camera ready paper due: Friday, May 8, 2015
-TALN Chair: Nadine Lucas GREYC, Université Caen Basse Normandie, France -TALN Co-Chair: Gaël Dias GREYC, Université Caen Basse Normandie, France -RÉCITAL Chair: Charlotte Lecluze GREYC, Université Caen Basse Normandie, France -RÉCITAL Co-Chair: Jose G Moreno GREYC, Université Caen Basse Normandie, France
(2015-06-22) Natural Language Processing Students Conference, Univ.Caen, Normandy, France
RECITAL 2015 : Call for Papers ------------------------------------
17th Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RECITAL)
(Natural Language Processing Students Conference)
University of Caen Lower Normandy, June 22-25, 2015 - Caen, France
Important dates -----------------
- Submission deadline : Friday, March 20 2015 - Acceptance notification : Tuesday, April 28 2015 - Camera ready : Friday, May 15 2015
Presentation ------------
RECITAL 2015, the annual meeting for young researchers associated to the TALN conference, will take place in Caen (France) on June 22 to 25. RECITAL provides a venue for young researchers investigating topics in Computational Linguistics and Natural Language Processing to present their research, meet potential advisors, and receive feedback from the research community. Authors must be students (Master or Ph.D.) or young researchers who recently completed their Ph.d. RECITAL 2015 will include oral and poster presentations. The official language is French but English presentations and papers are accepted for non-French-speaking authors.
Building on the success of the previous year, we are encouraging the submission of research proposals and papers describing preliminary works (state-of-the-art, first experiments, etc.). RECITAL's main goal is to support the work of young researchers and facilitate their integration into our community. To this aim we enhance :
- pedagogic reviews : authors should be able to understand their mistakes and correct them in order to improve the quality of their work;
- positive reviews : it is never necessary to discourage a young researcher, watchwords will be encouraging/guiding;
- direct exchange : all the reviews will be signed. Authors and reviewers are encouraged to discuss together during the conference.
A prize will be awarded to the author(s) of the best paper during the closing ceremony.
A scholarship program is set up to help authors of accepted papers. These grants include travel to Caen and conference registration. They shall be granted after examination on a case-by-case requests and submitted papers.
A scholarship program is set up to help authors of accepted papers. These grants include travel to Caen and conference registration. They will be granted after examination of requests and submitted papers.
Topics ------
Relevant topics include, but are not limited to, the following areas (in alphabetical order):
- Analysis and generation in the following domains: + Phonetics + Phonology + Morphology + Syntax + Semantics + Discourse - Development of language resources for NLP: + Databases containing morphological, syntactic, semantic, and/or phonological information + Grammars + Lexicons + Ontologies + Corpus linguistics - NLP applications: + Opinion and Sentiment Analysis + Automatic Classification or Categorization + Word Sense Disambiguation + Human machine dialogue + Automatic Indexing + Information Retrieval and Extraction + Summarization + Anaphora resolution + Question-Answering + Machine Translation + Semantic Web - Approaches: + Formal Linguistics to support automatic processing + Automatic processing for experimental linguistics + Computational psycholinguistics + Symbolic + Logical + Statistical + Based on Machine Learning
Selection Criteria ------------------
Research Papers must describe original completed work or work in progress and should clearly indicate directions for future research wherever appropriate. Authors MUST be students (Master or Ph.D.) or young researchers who recently completed their Ph.D. Publications with confirmed researchers (which include Ph.D. supervisors) must be submitted to TALN.
Submissions will be reviewed by at least two experts in the field. In particular, will be considered:
- Correction of scientific and technical content - Comparison with previous works - The organization and clarity of presentation - The adequacy of the conference topics
The selected communications will be published in the conference proceedings.
Submission Procedure --------------------
Papers will be written in French for French-speaking authors or English for non-French-speaking authors. A LaTeX style file and a Word template will be available on the conference website (https://taln2015.greyc.fr/recital/).
Contact : Charlotte Lecluze and José Moreno University of Caen Lower Normandy, GREYC CNRS UMR 6072 firstname.lastname@unicaen.fr
(2015-06-29) 6èmes Journées de Phonétique clinique, Montpellier, France
1er appel à communication
6èmes Journées de Phonétique clinique
Montpellier 29 juin - 1er juillet 2015
Organisées pour la première fois à Paris en 2005 puis rééditées successivement à Grenoble (2007), Aix-en-Provence (2009), Strasbourg (2011) et Liège (2013), les Journées de Phonétique Clinique (JPC) réunissent des chercheurs et des ingénieurs mais aussi des médecins (ORL, phoniatres, chirurgiens,?) ainsi que des orthophonistes s?intéressant tous aux questions liées aux pathologies de la parole et du langage.
Les 6èmes Journées de Phonétique Clinique, qui font suite aux précédentes éditions, se dérouleront à Montpellier du 29 juin au 1er juillet 2015, où elles sont organisées conjointement par le laboratoire Praxiling (CNRS UMR 5267, Université Paul-Valéry), le Département Universitaire d?Orthophonie (Université Montpellier 1), l?Institut des Neurosciences de Montpellier (INSERM U1051) et le CHU Gui de Chauliac de Montpellier (service des troubles de la voix et de la déglutition).
L?objectif de ces Journées interdisciplinaires sera de faire progresser les connaissances fondamentales relatives à la communication parlée, dans le but de mieux comprendre, évaluer, diagnostiquer et remédier aux troubles de la production et de la perception de la parole, du langage et de la voix chez les sujets pathologiques.
Dans ce contexte, cette série de colloques internationaux représente une opportunité pour des professionnels, des chercheurs confirmés et des jeunes chercheurs de formations différentes de présenter des résultats expérimentaux nouveaux et d?échanger des idées de diverses perspectives. Ainsi, des données sur la production et la perception de la parole chez le sujet sain et chez le sujet pathologique peuvent être analysées de manière adéquate et des modèles peuvent être développés, de sorte que les mécanismes qui gouvernent la production et la perception de la parole puissent être mieux compris, et exploités efficacement, en particulier dans le cadre d?applications cliniques.
Les propositions de communications porteront ainsi sur les études de la parole et de la voix pathologiques, chez l?adulte et chez l?enfant.
Les thèmes des 6èmes Journées de Phonétique Clinique incluront donc, de façon non exhaustive, les problématiques suivantes :
· Perturbations du système oro-pharyngo-laryngé
· Parole et perturbations des systèmes perceptifs, auditifs et visuels
· Troubles cognitifs et moteurs de la parole et du langage
· Modélisation de la parole et de la voix pathologiques
· Évaluation fonctionnelle du langage, de la parole et de la voix.
· Diagnostic et traitement des troubles de la parole et de la voix parlée et chantée
· Instrumentation et ressources en phonétique clinique
- ?.
Pour cette 6° édition, une attention toute particulière sera accordée à la question innovante de la prise en charge des populations bilingues et/ou polyglottes. Ainsi, les propositions portant sur la question de l?adaptation (ou de l?inadaptation) des outils de dépistage et de prise en charge dans une perspective translinguistique et/ou transculturelle bénéficieront d?un intérêt tout particulier.
Dates Importantes
Deadline pour soumission des propositions de communication (résumé de 500 mots hors bibliographie) : 1er mars 2015
Ouverture de la plateforme de dépôt des propositions : 1er février 2015
(2015-07-01) CONSECUTIVITY AND SIMULTANEITY IN LINGUISTICS, LANGUAGES AND SPEECH, Strasbourg, France
CONSECUTIVITY AND SIMULTANEITY
IN LINGUISTICS, LANGUAGES AND SPEECH
CONFERENCE ORGANISED BY
THE RESEARCH UNIT 1339 LINGUISTIQUE, LANGUES, PAROLE (LILPA)
UNIVERSITY OF STRASBOURG (UNISTRA) / STRASBOURG (FRANCE)
AND
THE FACULTY OF ARTS
PAVOL JOZEF ŠAFÁRIK UNIVERSITY (UPJŠ) / KOŠICE (SLOVAKIA)
1st TO 3rd JULY 2015
STRASBOURG / FRANCE
This international and interdisciplinary conference focuses on original and innovative work on the complex dynamic character of the consecutivity/simultaneity couple in the field of linguistics. It covers all disciplines of linguistics, as well as other related scientific areas (e.g. information sciences, computer sciences, medicine, etc.) preoccupied resolutely by linguistic issues.
If the paradigm of consecutivity usually examines phenomena which succeed in time, in space and in a conceptual order, these consecution relationships can also denote dynamic interdependence between causality and simultaneity; the latter referring to phenomena which occur at the same time.
In the field of semantics and syntax, some linguistic categories illustrate temporal properties (gerund, the past participle, etc.) and aspectual properties (accomplished, unaccomplished, durational, etc.) of consecutivity and/or simultaneity. Similarly, temporal markers such as and, then, etc., are characterised by their ability to alternatively denote these two properties. Finally, some syntactic constructions, including textual ones, induce through their own iconicity, spatiotemporal interpretation (incidence vs dependence, correlation vs causality, etc.).
Regarding languages, interpretation, unlike translation, carried out either consecutively (with or without taking down notes) or simultaneously (in the cabin or outside the cabin – 'chuchotage'), relies mainly on reformulation strategy, this re-expression technique being more rapid and more salient in the context of simultaneous interpretation.
As concerns texts, we shall consider the intricacies of relationships between diachronic and synchronic variations observable in manuscripts, and also syntactic twists or semantic constants.
In didactics of first and foreign languages, it is useful to observe how opposing the simultaneous to the consecutive determines institutional didactic choices (e.g. notional vs action perspective), expert choices (direct vs deferred or face-to-face vs mediated teaching, etc.) and also pedagogical choices (spontaneous vs reformulated production, active vs imitative approach, etc.).
In sociolinguistic investigations carried out by dialectologists, investigators are confronted with linguistic and meta-linguistic formulations of informants, formulations that these very informants may change, for various reasons and at different times of the investigation. It is the tension between consecutivity and simultaneity of productions of the same speaker which help to adequately approach the object of one’s study, and better understand language changes
observed by researchers, together with the reasons for linguistic repositioning carried out by informants.
In speech production and speech perception, we shall confront the (quasi)sequential representation of phonetic and phonological segments within a phonetic and phonological gestural analysis, in terms of coarticulation of segments, or even in terms of their co-production. We shall argue that co-production of articulatory gestures serves to optimise rapid and global perception of speech.
Proposals should highlight, in one of the themes mentioned below:
1) Either the study of a given problem within the linguistic sciences, related to the analysis of consecutivity and simultaneity;
2) Either an issue allowing improvement or development of methods, tools and procedures for the analysis of consecutivity and simultaneity in a field of linguistics.
In all cases, the perspective adopted by the conference will be met to and clarified.
OFFICIAL LANGUAGES OF THE SYMPOSIUM: FRENCH AND ENGLISH
THEMES OF THE CONFERENCE
Different themes or research areas may be considered as part of this call for papers, among which would include, but are not limited to: Analysis of manuscripts
Discourse analysis
Databases
Contact languages and cultures
Foreign language didactics
French didactics
Lexicology
Modelling
Morphology
Oral / Written forms
Philosophy of Language
Phonetics and phonology
Clinical linguistics and phonetics
Multilingualism
Language policy
Pragmatics
Speech production and perception
Semantics
Semiotics
Syntax
Acquisition systems and tools
Translation and Interpretation
Translation
Automatic processing of natural languages
TERMS OF SUBMISSION
Proposals should include the following information:
– Title of the paper;
– Outline of the problem of the study providing all relevant details;
– 4-5 keywords.
The entire contribution will not exceed four pages, including references (Times 12, 1.5 spacing).
Proposals will be submitted online, and will be subject to evaluation by the Scientific Committee and by a team of evaluators.
IMPORTANT DATES
♦ Dissemination of the call for papers: November 10, 2014
♦ Opening of the site for the submission of 2-4 page abstracts: December 1, 2014
♦ Deadline for submission: January 18, 2015
♦ Notification: March 29, 2015
♦ Registration opens:
– Early Bird registration: March 30 to April 26, 2015 (special tariff for students / PhD)
– Full tariff registration: from 27 April 2015
♦ Registration deadline: May 18, 2015
♦ Date of the conference: 1 to 3 July 2015
ORGANISERS
LILPA Research Unit (Linguistics, Languages & Speech), Dir. Rudolph Sock
Research Teams (E.R.) composing the Unit:
• Language Didactics (Dir. Laurent Kashema)
• Discourse Functioning and Translation (Dir. Maryvonne Boisseau)
• Research Groupe on European Multilingualism (Dir. Dominique Huck)
• Speech and Cognition (Dir. Béatrice Vaxelaire)
• Scolia (Dir. Pierre Nobel)
Faculty of Arts of Pavol Jozef Šafárik University in Košice (UPJŠ) / Košice (Slovakia):
Workshop in conjunction with IJCAI 2015 Buenos Aires, Argentina, July 25-27 2015
Motivation and Aims Natural Language Processing is becoming more and more ubiquitous as technologies become omnipresent in our daily life. This involves a huge effort to develop language-based interfaces, text analytics, search engines, writing assitants among other systems and their related tools and resources. Adaptation has been key to facilitate rapid development of language-based systems, with reuse of existing resources as alternatives to creating tools and resources from scratch. These approaches have benefited from the recent surge of complex Machine Learning approaches as applied to NLP tasks. This is the case for Semi-supervised and Unsupervised Learning, Active Learning, Domain Adaptation, and even Representation Learning and Deep Learning, which have had a very positive impact on NLP tasks and applications.
This workshop aims to provide a meeting point for researchers working on the portability of language resources and methodologies across languages and domains, with a special focus on exploiting available knowledge as a base to facilitate and enhance new developments. We understand that there is a common factor between tasks like porting a parser between related languages, adapting a dialogue system for a different domain, using rules inferred from an annotated corpus together with an unannotated corpus to port an information extraction system to another domain, or simplifying texts for different kinds of readers, among others. We believe that sharing insights on such approaches will be enriching and will contribute to a better understanding of the problems and solutions.
We expect that themes like Representation Learning, Deep Learning and Active Learning, and their successful applications to various areas of NLP, will raise interesting, intellectually challenging discussions.
Workshop Topics Contributions may present results from completed as well as ongoing research, with an emphasis on novel approaches, methods, ideas, and perspectives.
The topics of the workshop include, but are not limited to:
Semi-supervised learning, Deep Learning, Active learning and Representation learning for domain adaptation, language portability and task portability Adaptation and reuse of tools and resources for closely related languages Adaptation of highly valuable resources, like treebanks, to languages not closely related Linguistic issues in language portability: false friends, asymmetric discretization of semantic continuum Learning from multiple domains Development of multi-domain datasets Evaluation paradigms for complex learning Domain adaptation for specific applications: parsing, machine translation, information extraction, document classification, sentiment analysis and author attribution and profiling
Format of submissions Submissions are invited for papers presenting high quality, previously unpublished research. Selection criteria include originality of ideas, correctness, clarity and significance of results and quality of presentation.
We welcome two types of contributions:
Long papers (10 pages), presenting substantial, original and completed research work. Accepted long papers will be presented orally. Short papers (6 pages), with a small, focused contribution, work in progress, a negative result or an opinion piece. Accepted short papers will be presented either orally or as a poster.
Short papers can be combined with a system demonstration.
The only accepted format for submitting papers is Adobe PDF. Papers should follow IJCAI-15 formatting Guidelines.
As the review process will be double-blind, your submission must not include the author(s) name(s) and affiliation(s). Furthermore, self-references that reveal the author's identity, e.g., 'We previously showed (Pérez, 2003) ...', must be avoided. Instead, citations such as 'Pérez (2003) previously showed ...', must be used.
Submissions will be electronic, the submission site will be made available soon.
Important Dates Submission deadline: April 27 2015 Acceptance/rejection notification: May 20 2015 Camera-ready deadline: May 30, 2015 Workshop: July 25-27 2015 at IJCAI 2015
Programme Committee Luciana Benotti (UNC, Argentina) Xavier Carreras (XEROX-XRCE, France) Helena Caseli (UFSCar, Brazil) José Castaño (UBA, Argentina) Carlos Iván Chesñevar (UNS, Argentina) Martín Domínguez (UNC, Argentina) Pablo Duboue (Les Laboratoires Foulab, Canada) Marcelo Errecalde (UNSL, Argentina) Hugo Jair Escalante (INAOE, Mexico) Paula Estrella (UNC, Argentina) Mikel Forcada (UA, Spain) Maria Fuentes Fort (UPC, Spain) Xavier Gómez Guinovart (UVigo, Spain) Agustín Gravano (UBA, Argentina) Franco Luque (UNC, Argentina) Rada Mihalcea (UNT, USA) Maria das Graças Volpe Nunes (USP, Brazil) Lluís Padró (UPC, Spain) Muntsa Padró (Nuance, Canada) Martí Quixal (UTübingen, Germany) Thiago Pardo (USP, Brazil) Ted Pedersen (UMN, USA) German Rigau (UPV, Spain) Aiala Rosá (UdelaR, Uruguay) Paolo Rosso (UV, Spain) Horacio Saggion (UPF, Spain) Thamar Solorio (UH, USA) Juan-Manuel Torres-Moreno (LIA/UAPV, France) Cristina Vertan (UH, Germany) Dina Wonsever (UdelaR, Uruguay)
Organizing Committee
Laura Alonso i Alemany (UNC, Argentina) Núria Bel (UPF, Spain) Irene Castellón (UB, Spain) Manuel Montes y Gómez (INAOE, Mexico) -- Núria Bel /Professora Agregada/
Institut Universitari de Lingüística Aplicada Departament de Traducció i Ciències del Llenguatge
(2015-07-31) CfP Workshop on Continuous Vector Space Models and their Compositionality (3rd edition), Beijing, China
Workshop on Continuous Vector Space Models and their Compositionality (3rd edition) Co-located with ACL 2015, Beijing, China July 31, 2015 Submission deadline: May 14, 2015 https://sites.google.com/site/cvscworkshop2015 ****************************************************************************************************
First Call for Papers
In recent years, there has been a growing interest in algorithms that learn and use continuous representations for words, phrases, or documents in many natural language processing applications. Among many others, influential proposals that illustrate this trend include latent Dirichlet allocation, neural network based language models and spectral methods. These approaches are motivated by improving the generalization power of the discrete standard models, by dealing with the data sparsity issue and by efficiently handling a wide context. Despite the success of single word vector space models, they are limited since they do not capture compositionality. This prevents them from gaining a deeper understanding of the semantics of longer phrases, sentences and documents.
Regarding this issue, some pertinent questions arise: should word/phrase/sentence representations be of the same sort? Could different linguistic levels require different modeling approaches ? Is compositionality determined by syntax, and if so, how do we learn/define it? Should word representations be fixed and obtained distributionally, or should the encoding be variable? Should word representations be task-specific, or should they be general?
In this workshop, we invite submissions of papers on continuous vector space models for natural language processing. Topics of interest include, but are not limited to: * Neural networks * Spectral methods * Distributional semantic models * Language modeling for automatic speech recognition, statistical machine translation, and information retrieval * Automatic annotation of texts * Phrase and sentence-level distributional representations * The role of syntax in compositional models * Formal and distributional semantic models * Language modeling for logical and natural reasoning * Integration of distributional representations with other models * Multi-modal learning for distributional representations * Knowledge base embedding
INVITED SPEAKERS
The workshop will showcase presentations from 4 to 6 keynote speakers. The confirmed speakers are: Yoav Goldberg (Bar Ilan University) Jason Weston (Facebook AI Research) Kyunghyun Cho (Université de Montréal)
SUBMISSION INFORMATION
Authors should submit a full paper of up to 8 pages in electronic, PDF format, with up to 2 additional pages for references. The reported research should be substantially original. The papers will be presented orally or as posters.
All submissions must be in PDF format and must follow the ACL 2015 formatting requirements (see the ACL 2015 Call For Papers http://acl2015.org/call_for_papers.html). Reviewing will be double-blind, and thus no author information should be included in the papers; self-reference should be avoided as well. Submissions must be made through the Softconf website set up for this workshop:
Accepted papers will appear in the workshop proceedings, where no distinction will be made between papers presented orally or as posters.
IMPORTANT DATES
14 May 2015 : Submission deadline 4 June 2015 : Notification of acceptance 21 June 2015 : Camera-ready deadline 31 July 2015 : Workshop
ORGANIZERS
Alexandre Allauzen (LIMSI-CNRS/Université Paris-Sud, France) Edward Grefenstette (University of Oxford, UK) Karl Moritz Hermann (University of Oxford, UK) Hugo Larochelle (Université de de Sherbrooke, Canada) Scott Wen-tau Yih (Microsoft Research, USA)
PROGRAM COMMITTEE (in construction)
Marco Baroni, University of Trento Yoshua Bengio, Université de Montreal Phil Blunsom, University of Oxford Antoine Bordes, Facebook Leon Bottou, Microsoft Stephen Clark, University of Cambridge Shay Cohen, University of Edinburgh Georgiana Dinu, University of Trento Kevin Duh, Nara Institute of Science and Technology Yoav Goldberg, Bar Ilan University Andriy Mnih, University College London Mehrnoosh Sadrzadeh, University of London Mark Steedman, University of Edinburgh Peter Turney, NRC Jason Weston, Facebook Guillaume Wisniewski, LIMSI-CNRS
(2015-08-04) 2nd INTERNATIONAL CONFERENCE ON ALGORITHMS FOR COMPUTATIONAL BIOLOGY, Mexico City
2nd INTERNATIONAL CONFERENCE ON ALGORITHMS FOR COMPUTATIONAL BIOLOGY
AlCoB 2015
Mexico City, Mexico
August 4-6, 2015
Organized by:
Centre for Complexity Sciences (C3) School of Sciences Institute for Research in Applied Mathematics and Systems (IIMAS) Graduate Program in Computing Science and Engineering National Autonomous University of Mexico
Research Group on Mathematical Linguistics (GRLMC) Rovira i Virgili University
AlCoB aims at promoting and displaying excellent research using string and graph algorithms and combinatorial optimization to deal with problems in biological sequence analysis, genome rearrangement, evolutionary trees, and structure prediction.
The conference will address several of the current challenges in computational biology by investigating algorithms aimed at: 1) assembling sequence reads into a complete genome, 2) identifying gene structures in the genome, 3) recognizing regulatory motifs, 4) aligning nucleotides and comparing genomes, 5) reconstructing regulatory networks of genes, and 6) inferring the evolutionary phylogeny of species.
Particular focus will be put on methodology and significant room will be reserved to young scholars at the beginning of their career.
VENUE:
AlCoB 2015 will take place in Mexico City, the oldest capital city in the Americas and the largest Spanish-speaking city in the world. The venue will be the main campus of the National Autonomous University of Mexico.
SCOPE:
Topics of either theoretical or applied interest include, but are not limited to:
Stephen Altschul (National Center for Biotechnology Information, Bethesda, USA) Yurii Aulchenko (Russian Academy of Sciences, Novosibirsk, Russia) Pierre Baldi (University of California, Irvine, USA) Daniel G. Brown (University of Waterloo, Canada) Yuehui Chen (University of Jinan, China) Keith A. Crandall (George Washington University, Washington, USA) Joseph Felsenstein (University of Washington, Seattle, USA) Michael Galperin (National Center for Biotechnology Information, Bethesda, USA) Susumu Goto (Kyoto University, Japan) Igor Grigoriev (DOE Joint Genome Institute, Walnut Creek, USA) Yike Guo (Imperial College, London, UK) Javier Herrero (University College London, UK) Karsten Hokamp (Trinity College Dublin, Ireland) Hsuan-Cheng Huang (National Yang-Ming University, Taipei, Taiwan) Ian Korf (University of California, Davis, USA) Nikos Kyrpides (DOE Joint Genome Institute, Walnut Creek, USA) Yun Li (University of North Carolina, Chapel Hill, USA) Jun Liu (Harvard University, Cambridge, USA) Mingyao Li (University of Pennsylvania, Philadelphia, USA) Rodrigo López (European Bioinformatics Institute, Hinxton, UK) Andrei N. Lupas (Max Planck Institute for Developmental Biology, Tübingen, Germany) B.S. Manjunath (University of California, Santa Barbara, USA) Carlos Martín-Vide (chair, Rovira i Virgili University, Tarragona, Spain) Tarjei Mikkelsen (Broad Institute, Cambridge, USA) Henrik Nielsen (Technical University of Denmark, Lyngby, Denmark) Christine Orengo (University College London, UK) Modesto Orozco (Institute for Research in Biomedicine, Barcelona, Spain) Christos A. Ouzounis (Centre for Research & Technology Hellas, Thessaloniki, Greece) Manuel Peitsch (Philip Morris International R&D, Neuchâtel, Switzerland) David A. Rosenblueth (National Autonomous University of Mexico, Mexico City, Mexico) Julio Rozas (University of Barcelona, Spain) Alessandro Sette (La Jolla Institute for Allergy and Immunology, USA) Peter F. Stadler (University of Leipzig, Germany) Guy Theraulaz (Paul Sabatier University, Toulouse, France) Alfonso Valencia (Spanish National Cancer Research Centre, Madrid, Spain) Kai Wang (University of Southern California, Los Angeles, USA) Lusheng Wang (City University of Hong Kong, Hong Kong) Zidong Wang (Brunel University, Uxbridge, UK) Harel Weinstein (Cornell University, New York, USA) Jennifer Wortman (Broad Institute, Cambridge, USA) Jun Yu (Chinese Academy of Sciences, Beijing, China) Mohammed J. Zaki (Rensselaer Polytechnic Institute, Troy, USA) Louxin Zhang (National University of Singapore, Singapore) Hongyu Zhao (Yale University, New Haven, USA)
ORGANIZING COMMITTEE:
Adrian Horia Dediu (Tarragona) Francisco Hernández-Quiroz (Mexico City) Carlos Martín-Vide (Tarragona, co-chair) David A. Rosenblueth (Mexico City, co-chair) Florentina Lilica Voicu (Tarragona)
SUBMISSIONS:
Authors are invited to submit non-anonymized papers in English presenting original and unpublished research. Papers should not exceed 12 single-spaced pages (including eventual appendices, references, proofs, etc.) and should be prepared according to the standard format for Springer Verlag's LNCS series (see http://www.springer.com/computer/lncs?SGWID=0-164-6-793341-0).
A volume of proceedings published by Springer in the LNCS/LNBI series will be available by the time of the conference.
A special issue of a major journal will be later published containing peer-reviewed substantially extended versions of some of the papers contributed to the conference. Submissions to it will be by invitation.
Paper submission: March 2, 2015 (23:59 CET) Notification of paper acceptance or rejection: April 10, 2015 Final version of the paper for the LNCS/LNBI proceedings: April 19, 2015 Early registration: April 19, 2015 Late registration: July 21, 2015 Submission to the journal special issue: November 6, 2015
eNTERFACE workshops gather in a single place a team of senior project leaders, researchers, and students, to work on a pre-specified list of challenges for 4 weeks. Participants are organized in teams, each team being attached to a specific project.
If you are a senior/junior researcher or a PhD/MS/undergraduate student working on similar topics and you want to collaborate in (at least) one of these projects, please fill out the online registration form. You will be asked to upload a short CV in electronic format (doc, docx or pdf) along with a list of skills you can offer to the selected project teams. You can choose up to three projects. The project leaders will select their team members among the applicants.
The workshop attendance is free of charge but participants must fund their own travel, accommodation, and living expenses. The estimated costs are as follows :
Accommodation in single bedrooms in the University Residence Hall costs from 285? to 329?, (depending on bedclothes renting or not), per person for the whole one-month stay.
Meals (in the city) will cost about 400? for the 4 weeks, but this can be reduced by about a half if you eat at the university canteen at lunch time and cook for yourself at the dorm for dinner.
What are eNTERFACE workshops?
The eNTERFACE workshops aim at establishing a tradition of collaborative, localized research and development work by gathering, in a single place, a team of leading professionals in multimodal human-machine interfaces together with students (both graduate and undergraduate), to work on a prespecified list of challenges, for 4 complete weeks. In this respect, it is an innovative and intensive collaboration scheme, designed to allow researchers to integrate their software tools, deploy demonstrators, collect novel databases, and work side by side with a great number of experts. It brings together 80 researchers for a whole month, subsequently it is the largest summer workshop on multimodal interfaces.
The workshop is held on an annual basis and organized around several research projects dealing with multimodal human-machine interfaces design. It is thus radically different from traditional scientific workshops, in which only specialists meet for a few days to discuss state-of-the art problems, but do not really work together.
The eNTERFACE was initiated by the FP6 Network of Excellence SIMILAR. After the completion of SIMILAR, the workshop continued to attract wide interest under the aegis of the OpenInterface Foundation. It was organized by Faculté Polytechnique de Mons (Belgium) in 2005, University of Zagreb (Croatia) in 2006, Bogaziçi University (Turkey) in 2007, CNRS-LIMSI (France) in 2008, University of Genova (Italy) in 2009, University of Amsterdam (The Netherlands) in 2010, University of West Bohemia (Czech Republic) in 2011, Metz Supélec (France) in 2012, New University of Lisbon (Portugal) in 2013, and University of Basque Country (Spain) in 2014.
How does it work?
Experienced researchers are invited to propose research projects to be undertaken by a few people (5-10) during 4 weeks. The proposal should explain what to do, how many people are necessary, profile of these people, etc.
Once the projects have been supervised and approved by the technical committee, they are listed on this website.
Then there is a call for participation (*this email*): students/researchers from all around the world send their CVs and choose the project they prefer according to their expertise or interest.
Teams are built by the project leaders in cooperation with the organizers according to the preferences of the students/researchers and their suitability for the project.
Finally, the team members come to Mons and spend four wonderful and productive weeks together. There is no registration fee for participants and accommodation will be relatively cheap.
The team undertaking eNTERFACE 2015 is part of the NUMEDIART Institute for Creative Technology, with internationally recognised appraisal in the field of sound, image, video, gestures and biosignals processing for applications where human-computer interaction aims to prompt emotion.
(2015-08-20) IVA 2015 Doctoral Consortium, Delft, The Netherlands
IVA 2015 Doctoral Consortium, August 24th in Delft, The Netherlands http://iva2015.tudelft.nl -------------------------------------------------------------------
The Intelligent Virtual Agents (IVA) 2015 Doctoral Consortium will be held on Monday, the 24th of August, two days before the main IVA conference (26th of August - 28th of August, 2015). We invite and encourage PhD students working in the area of virtual agents to present and discuss their work. PhD students working on human-human and human-robot interaction with a relevance to intelligent virtual agents are also encouraged to apply.
The doctoral consortium offers PhD students the opportunity to discuss and present their research plans and progress to peers and experts in an interactive way. During the doctoral consortium, several distinguished researchers will provide feedback and guidance on the students' current research and future research directions. Students who would like to benefit from this feedback and guidance are welcome to apply. Students who have a clear topic and have already made some progress are especially encouraged to apply.
Based on the student's application, the organizing committee will select a group of students that will be invited to participate. The students selected are expected to attend and to give an oral presentation at the Doctoral Consortium. Students will also be given the possibility to present a poster during the poster session of the main conference.
-------------------------------------- Submission Guidelines and Instructions -------------------------------------- In order to apply for the doctoral consortium, the PhD student should follow these submission guidelines and instructions:
1. An application describing the student’s current and planned research should be submitted in the IVA paper format (see http://iva2015.tudelft.nl/?q=node/4) 2. Applications should be submitted as PDF documents (not exceeding 6 pages) through the IVA submission system http://iva2015.confmaster.net/ (select the doctoral consortium option).
Applications should be well written and organized. They should clearly describe:
* Aim(s) and objective(s) of the research * The challenge(s) that the student's research is addressing * The approach and method(s) used by the student to address the objective(s) and challenge(s) * The current status of the student's research and future directions * Optional: Specific issues or questions the student seeks feedback on at the consortium
--------------- Important dates --------------- * Submission deadline: 15th of March 2015 * Notification date: 6th of April 2015
--------------------- Contact and questions --------------------- Khiet Truong, University of Twente, k.p.truong@utwente.nl Hannes Vilhjalmsson, Reykjavik University, hannes@ru.is
LVA 2015 will be the 12th in a series of international conferences which attracted hundreds of researchers and practitioners over the years. Since its start in 1999 under the banner of Independent Component Analysis and Blind Source Separation (ICA), the conference has continuously broadened its horizons. It encompasses today a host of additional forms and models of general mixtures of latent variables. Theories and tools borrowing from the fields of signal processing, applied statistics, machine learning, linear and multilinear algebra, numerical analysis and optimization, and numerous application fields offer exciting interdisciplinary interactions.
*Highlights*
The conference will be preceded by a Summer School on Latent Variable Analysis and Signal Separation and it will feature the much-awaited results of the 5th Signal Separation Evaluation Campaign (SiSEC 2015).Keynote talks will be given by three leading researchers:- Tülay Adali (University of Maryland, Baltimore County, USA)- Rémi Gribonval (Inria, France)- DeLiang Wang (Ohio State University, USA)
*Call for Papers*
The proceedings will be published in Springer-Verlag's Lecture Notes in Computer Science Series (LNCS). Prospective authors are invited to submit original papers (up to 8 pages in LNCS format) in areas related to latent variable analysis and signal separation, including but not limited to:- Theory: sparse coding, dictionary learning; statistical and probabilistic modeling; detection, estimation and performance criteria and bounds; causality measures; learning theory; convex/nonconvex optimization tools- Models: general linear or nonlinear models of signals and data; discrete, continuous, flat, or hierarchical models; multilinear models; time-varying, instantaneous, convolutive, noiseless, noisy, over-complete, or under-complete mixtures- Algorithms: estimation, separation, identification, detection, blind and semi-blind methods, non-negative matrix factorization, tensor decomposition, adaptive and recursive estimation; feature selection; time-frequency and wavelet based analysis; complexity analysis- Applications: speech and audio separation, recognition, dereverberation and denoising; auditory scene analysis; image segmentation, separation, fusion, classification, texture analysis; biomedical signal analysis, imaging, genomic data analysis, brain-computer interface- Emerging related topics: sparse learning; deep learning; social networks; data mining; artificial intelligence; objective and subjective performance evaluation.
*Special Sessions*
The program will also feature special sessions on new or emerging topics of interest. Proposals for special sessions must include the session title, rationale, outline, and a list of 4 to 6 invited papers. To submit, see http://amca.cz/lva2015/.
*Important Dates*
Jan 16, 2015: Submission of special session proposals
Jan 30, 2015: Special session decisions announced
Mar 27, 2015: Paper submission deadline
May 22, 2015: Notification of acceptance
Jun 12, 2015: Submission of camera-ready papers
Aug 26-28, 2015: Conference dates Jan 16, 2015: Submission of special session proposals
*Organizing Committee*
General chairs:Zbynek Koldovsky (Technical University of Liberec, Czech Republic)Petr Tichavsky (Academy of Sciences, Czech Republic)Program chairs:Arie Yeredor (Tel-Aviv University, Israel)Emmanuel Vincent (Inria, France)Special sessions: Shoji Makino (University of Tsukuba, Japana)SiSEC chair: Nobutaka Ono (NII, Japan)Overseas liaison: Andrzej Cichocki (RIKEN, Japan)
(2015-08-27) 2nd CfP 25th Annual Conference of the European Second Language Association 5EUROSLA 2015),Université d'Aix-Marseille, France
** Second Call for Papers **
UMR 7309 Laboratoire Parole et Langage (Université d?Aix-Marseille), in association with the Département de français langue étrangère (Pôle LLC, UFR ALLSHS, Université d?Aix- Marseille), is pleased to announce that it will host EUROSLA 25, the 25th Annual Conference of the European Second Language Association. The general theme of the Conference is « Second Language Acquisition : Implications for language sciences?. You are kindly invited to submit abstracts for papers, posters, thematic colloquia and doctoral workshop related to this theme or to any other domain and subdomain of second language research.
The Conference will start in the morning of 27 August 2015 and close at 12 a.m on 29 August 2015. Preceding the Conference, there will be a doctoral workshop and a Language Learning roundtable, both on 26 August 2015. The theme of this year?s roundtable is ?SLA and theories of pidginization / creolization?.
- Gabriele PALLOTI (Università degli Studi di Modena e Reggio Emilia (UNIMORE))
Key dates:
- 1 February 2015: Early bird registration
- 27February 2015: Abstract submission deadline
- 24 April 2015: Notification of acceptance
- 1 June 2015: Full fee registration starts
- 18 July 2015: End of registration
Language Policy
EUROSLA 25 will be a bilingual conference (English and French) ; presentations in one of these languages are particularly encouraged. However, following the Eurosla constitution, any other European language may also be used.
Abstract submission policy
Each author may submit no more than one single-authored and one co-authored (i.e. not first-authored) abstract to be considered for oral presentations, including colloquia and doctoral workshops. More than one abstract can be submitted for poster presentations. Paper and poster proposals should not have been previously published. All submissions will be reviewed anonymously by the scientific committee and evaluated in terms of rigour, clarity and significance of the contribution, as well as its relevance to second language research. Abstracts should not exceed 500 words (excluding the title, but including optional references).
Individual papers and posters
Papers will be allocated 20 minutes for presentation plus 5 minutes for discussion.
Poster sessions will be held in two 90-minute slots. In order to foster interaction, all other sessions will be suspended during the poster sessions.
Thematic colloquia
The Thematic colloquia will be organised in two-hour slots running in parallel with other sessions. Each colloquium will focus on one specific topic, and will bring together contributions to the topic. Each thematic colloquium should include a maximum of 4 presentations. Colloquium convenors should allocate time for opening and closing remarks, individual papers, discussants (if included) and general discussion.
Doctoral student workshop
The doctoral student workshop is intended to serve as a platform for discussion of ongoing PhD research within any aspect of second language research. PhD students are invited to submit an abstract for a 10-15-minute presentation. The Doctoral workshop focuses on problems of methodology with regard to either data analysis (interpretation of natural conversation, statistical data, interviews, etc.) or research design (experimental design, corpus design, issues of data collection, etc.). These sessions are not intended as opportunities to present research results, but to discuss future directions. Students whose abstracts are accepted will be required to send their paper to a discussant (a senior researcher). The discussant will lead a 10-15-minute feedback/discussion session on their work.
Student stipends
?As in previous years, several student stipends will be available for doctoral students.?If you wish to apply, please send the following information to 25.eurosla@gmail.com before 27 February 2015:
1. Name, institution, and address of institution;
2. Curriculum vitae (attached);
3. Official confirmation of a PhD student status;
4. Statement (email) from supervisor or head of Department that the applicant?s institution cannot (fully) cover the conference-related expenses.
Publication of papers
?
A selection of papers presented at EUROSLA 2015 will be published in the EUROSLA 25 or 26 Yearbook following a peer-review process. There is an annual prize for the best EUROSLA Yearbook article. This includes a framed certificate presented at the EUROSLA General Assembly, a fee waiver for the following EUROSLA conference and conference dinner, and free EUROSLA membership for a year.
Université d?Aix-Marseille, Aix-en-Provence, France
** Final Call for Papers **
UMR 7309 Laboratoire Parole et Langage (Université d?Aix-Marseille), in association with the Département de français langue étrangère (Pôle LLC, UFR ALLSHS, Université d?Aix- Marseille), is pleased to announce that it will host EUROSLA 25, the 25th Annual Conference of the European Second Language Association. The general theme of the Conference is « Second Language Acquisition : Implications for language sciences?. You are kindly invited to submit abstracts for papers, posters, thematic colloquia and doctoral workshop related to this theme or to any other domain and subdomain of second language research.
The Conference will start in the morning of 27 August 2015 and close at 12 a.m on 29 August 2015. Preceding the Conference, there will be a doctoral workshop and a Language Learning roundtable, both on 26 August 2015. The theme of this year?s roundtable is ?SLA and theories of pidginization / creolization?.
- Gabriele PALLOTI (Università degli Studi di Modena e Reggio Emilia (UNIMORE))
Key dates:
- 1 February 2015: Early bird registration
- 27February 2015: Abstract submission deadline
- 24 April 2015: Notification of acceptance
- 1 June 2015: Full fee registration starts
- 18 July 2015: End of registration
Language Policy
EUROSLA 25 will be a bilingual conference (English and French) ; presentations in one of these languages are particularly encouraged. However, following the Eurosla constitution, any other European language may also be used.
Abstract submission policy
Each author may submit no more than one single-authored and one co-authored (i.e. not first-authored) abstract to be considered for oral presentations, including colloquia and doctoral workshops. More than one abstract can be submitted for poster presentations. Paper and poster proposals should not have been previously published. All submissions will be reviewed anonymously by the scientific committee and evaluated in terms of rigour, clarity and significance of the contribution, as well as its relevance to second language research. Abstracts should not exceed 500 words (excluding the title, but including optional references).
Individual papers and posters
Papers will be allocated 20 minutes for presentation plus 5 minutes for discussion.
Poster sessions will be held in two 90-minute slots. In order to foster interaction, all other sessions will be suspended during the poster sessions.
Thematic colloquia
The Thematic colloquia will be organised in two-hour slots running in parallel with other sessions. Each colloquium will focus on one specific topic, and will bring together contributions to the topic. Each thematic colloquium should include a maximum of 4 presentations. Colloquium convenors should allocate time for opening and closing remarks, individual papers, discussants (if included) and general discussion.
Doctoral student workshop
The doctoral student workshop is intended to serve as a platform for discussion of ongoing PhD research within any aspect of second language research. PhD students are invited to submit an abstract for a 10-15-minute presentation. The Doctoral workshop focuses on problems of methodology with regard to either data analysis (interpretation of natural conversation, statistical data, interviews, etc.) or research design (experimental design, corpus design, issues of data collection, etc.). These sessions are not intended as opportunities to present research results, but to discuss future directions. Students whose abstracts are accepted will be required to send their paper to a discussant (a senior researcher). The discussant will lead a 10-15-minute feedback/discussion session on their work.
Student stipends
?As in previous years, several student stipends will be available for doctoral students.?If you wish to apply, please send the following information to 25.eurosla@gmail.com before 27 February 2015:
1. Name, institution, and address of institution;
2. Curriculum vitae (attached);
3. Official confirmation of a PhD student status;
4. Statement (email) from supervisor or head of Department that the applicant?s institution cannot (fully) cover the conference-related expenses.
Publication of papers
?
A selection of papers presented at EUROSLA 2015 will be published in the EUROSLA 25 or 26 Yearbook following a peer-review process. There is an annual prize for the best EUROSLA Yearbook article. This includes a framed certificate presented at the EUROSLA General Assembly, a fee waiver for the following EUROSLA conference and conference dinner, and free EUROSLA membership for a year.
(2015-08-31) CfP EUSIPCO 2015, Nice, France (updated)
EUSIPCO 2015 CALL FOR PAPERS NICE, COTE D'AZUR, FRANCE 31st AUGUST - 4th SEPTEMBER 2015
EUSIPCO is the flagship conference of the European Association for Signal Processing (EURASIP). The 23rd edition will be held in Nice, on the French Riviera, from 31st August 4th September 2015. EUSIPCO 2015 will feature world-class speakers, oral and poster sessions, keynotes, exhibitions, demonstrations and tutorials and is expected to attract in the order of 600 leading researchers and industry figures from all over the world.
TECHNICAL SCOPE The focus will be on signal processing theory, algorithms, and applications. We invite the submission of original, unpublished technical papers on topics including but not limited to: -Audio and acoustic signal processing -Machine learning -Speech processing -Signal processing for education -Image and video processing -Design and implementation of signal processing systems -Multimedia signal processing -Signal processing theory and methods -Information forensics and security -Sensor array, multichannel and communications signal processing -Bio-inspired image and signal processing -Medical image and signal processing -Nonlinear signal processing -Signal processing applications
Accepted papers will be included in IEEEXplore. Paper submission details are available at the conference website: www.eusipco2015.org.
BEST STUDENT PAPER AWARDS Two 'EUSIPCO Best Student Paper Awards' will be presented at the conference banquet. Papers will be selected by a committee composed of area and technical chairs.
LOCATION AND VENUE Nestled between the foot of the Alpes and the Mediterranean Sea, the location can be accessed easily from the Nice Cote d'Azur international airport, France's busiest outside of Paris, with direct connections to almost 100 European destinations and 14 international destinations including New York (JFK) and Dubai. The conference will be held at the Nice Acropolis Convention Centre, named 'Europe's number one convention centre' for three consecutive years. The Acropolis is located in the heart of the city only minutes away from the Promenades des Anglais and the Baie des Anges.
IMPORTANT DATES -Special session proposals: 1st December 2014
-Tutorial proposals: 13th February 2015
-Full paper submissions: 13th February 2015 extended to February 27th
-Notification of acceptance: 22nd May 2015
-Camera-ready papers: 19th June 2015
ORGANIZING COMMITTEE General chairs Jean-Luc Dugelay (EURECOM) Dirk Slock (EURECOM)
Technical chairs Marc Antonini (I3S/UNS/CNRS) Nicholas Evans (EURECOM) Cedric Richard (UNS/OCA)
International Liaisons Thierry Blu (CUHK) Mohamed Deriche (KFUPM) Douglas O'Shaughnessy (INRS) Kenneth Rose (UCSB)
CONFERENCE SECRETARIAT EURECOM, Campus SophiaTech, 450 Route des Chappes, 06410 Biot, FRANCE E-mail: info@eusipco2015.org Website: www.eusipco2015.org
-- ---------------------------------------------- Special issue on Biometric Spoofing and Countermeasures IEEE TRANS. INFORMATION FORENSICS AND SECURITY http://www.eurecom.fr/~evans/docs/TIFSsi.pdf ---------------------------------------------- Special issue on Biometric Security and Privacy IEEE Signal Processing Magazine http://www.eurecom.fr/~evans/docs/SPMsi.pdf ---------------------------------------------- 23rd European Signal Processing Conference (EUSIPCO) 2015 in NICE http://www.eusipco2015.org ---------------------------------------------- Nick Evans EURECOM Multimedia Communications Dept. Campus SophiaTech 450 route des Chappes 06410 Biot Sophia Antipolis FRANCE
MediaEval 2015 Multimedia Benchmark Call for Survey Participation ***********************************
The MediaEval 2015 season kicks off with the MediaEval Multimedia Benchmark Task Survey. The survey collects the input of the research community about which challenges should be offered by MediaEval in 2015.
Please add your email address to the survey, in order to receive more information specifically about 2015.
MediaEval (http://www.multimediaeval.org) is a benchmarking initiative dedicated to evaluating new algorithms for multimedia access and retrieval. It emphasizes the 'multi' in multimedia and focuses on human and social aspects of multimedia tasks.
MediaEval attracts participants who are interested in multimodal approaches to multimedia involving, e.g., speech recognition, visual analysis, audio analysis, music and musical scores, user-contributed information (tags, comments), viewer affective response, social networks, user privacy, geo-coordinates and crowdsourcing.
The survey asks you questions about the 13 tasks that have been proposed for MediaEval 2015. It will take you about 5 minutes if you fill in only the main questions. It will take about 30 minutes if you choose to answer the additional questions and give comments. We encourage you to answer the additional questions on the tasks that most interest you. Your answers contribute to decisions than are made about the design and implementation of the tasks.
The MediaEval 2015 task list will be finalized and sign up for participation will open at the end of February. Please be sure to fill your email address in on the first page of the survey if you would like to receive a mail when sign up opens.
Our goal is to have the survey filled out by as many researchers as possible in the next three weeks?please pass the survey link along to colleagues in the field of multimedia who might be interested.
Note that the deadline for results submissions this year will be the end of August. The MediaEval 2015 workshop will be held 14-15 September near Dresden, Germany. It is a satellite event of Interspeech 2015, which takes place in Dresden.
The ISCA (International Speech Communication Association) Special Interest Group (SIG) on Speech and Language Technology in Education (SLaTE) promotes the use of speech and language technology for educational purposes, and provides a forum for exchanging information regarding recent developments and other matters of interest related to this topic. For further information please visit http://www.sigslate.org.
The workshop will be held in Leipzig, September 4–5, 2015. It is a satellite event of the 16th Annual Conference of the International Speech Communication Association (INTERSPEECH 2015), which will take place afterwards in Dresden, September 6–10, 2015. Dresden is only 120 km away from Leipzig and can be reached easily within 72 minutes by train (ICE).
If you are interested, please download our flyer or our posters (poster 1 and poster 2). We will present them at the INTERSPEECH 2015 booth at INTERSPEECH 2014 in Singapore.
Growing amounts of multimedia content is being shared or stored in online archives. Alternative research directions in the speech processing and multimedia analysis communities are developing and improving speech or multimedia processing technologies in parallel, often using each others work as ?black boxes?. However, genuine combination would appear to be a better strategy to exploit the synergies between the modalities of content containing multiple potential sources of information.
This session seeks to bring together the speech and multimedia research communities to report on current work and to explore potential synergies and opportunities for creative research collaborations between speech and multimedia technologies. From the speech perspective the session aims to explore how fundamentals of speech technology can be benefit multimedia applications, and from the multimedia perspective to explore the crucial role that speech can play in multimedia analysis.
The list of topics of interest includes (but is not limited to):
- Navigation in multimedia content using advanced speech analysis features; - Large scale speech and video analysis - Multimedia content segmentation and structuring using audio and visual features; - Multimedia content hyperlinking and summarization; - Natural language processing for multimedia; - Multimodality-enhanced metadata extraction, e.g. entity extraction, keyword extraction, etc; - Generation of descriptive text for multimedia; - Multimedia applications and services using speech analysis features; - Affective and behavioural analytics based on multimodal cues; - Audio event detection and video classification; - Multimodal speaker identification and clustering.
Important dates:
20 Mar 2015 paper submission deadline 01 Jun 2015 paper notification of acceptance/rejection 10 Jun 2015 paper camera-ready 20 Jun 2015 early registration deadline 6-10 Sept 2015 Interspeech 2015, Dresden, Germany
Submission takes place via the general Interspeech submission system. Paper contributions must comply to the INTERSPEECH paper submission guidelines, cf. http://interspeech2015.org/papers. There will be no extension to the full paper submission deadline. We are looking forward to receive your contribution!
Organizers:
- Maria Eskevich, Communications Multimedia Group, EURECOM, France (maria.eskevich@eurecom.fr <mailto:maria.eskevich@eurecom.fr>) - Robin Aly, Database Management Group, University of Twente, The Netherlands (r.aly@utwente.nl <mailto:r.aly@utwente.nl>) - Roeland Ordelman, Human Media Interaction Group, University of Twente, The Netherlands (roeland.ordelman@utwente.nl < mailto:roeland.ordelman@utwente.nl>) - Gareth J.F. Jones, CNGL Centre for Global Intelligent Content, Dublin City University, Ireland (gjones@computing.dcu.ie < mailto:gjones@computing.dcu.ie>)
This conference brings together two established interdisciplinary conferences:
The International Symposium on Facial Analysis and Animation (FAA)
and
The International Conference on Auditory-Visual Speech Processing (AVSP)
Both conferences have a common focus on facial communication research. FAA focuses on facial animation analysis and synthesis addressed in the fields of computer graphics, computer vision and psychology. AVSP focuses on how auditory and visual speech information plays a role in human perception, machine recognition, and human-machine interaction.
The two conferences attract researchers from diverse fields, such as speech processing, computer graphics and computer vision, psychology, neuroscience, linguistics, robotics and electrical engineering.
The aim of this first joint conference is to bring together, from both academia and industry, the two communities of facial animation (FAA) and audiovisual speech (AVSP) to discuss research and exchange ideas, data and experiences.
* Topics
Submission of papers are invited in all areas of facial animation and auditory-visual speech processing including but not limited to:
- Acquisition of Facial Shape, Motion and Texture
- Facial animation and rendering techniques
- Facial Model Based Coding and Compression
- Facial Analysis and Animation for Mobile Applications
- Embodied Virtual Agents
- Visual and Audiovisual Speech Synthesis
- Human and machine recognition of audio-visual speech
- Human and machine models of multimodal integration
- Multimodal and perceptual processing of facial animation and audiovisual events
- Cross-linguistic studies of audio-visual speech processing
- Developmental studies of audio-visual speech processing
- Audio-visual prosody
- Emotion and Expressivity modeling
- Gestures accompanying speech and non-linguistic behavior
- Neuropsychology and neurophysiology of audio-visual speech processing
- Scene analysis using audio and visual speech information
- Data collection and corpora for audio-visual speech processing
The conference will be held in Vienna, Austria, 11.-13. September 2015. The session on September 11 will be devoted to FAA topics and those on September 12-13 to AVSP topics. The keynotes will present topics relevant to both communities.
* Important Dates:
8 May 2015: Deadline for paper submission
12 June 2015: Notification of acceptance
19 June 2015: Camera-ready paper
11-13 September 2015: Conference
Two types of submission are possible: Abstracts (1 page) for FAA and AVSP topics, and full papers (4 to 6 pages) for AVSP topics.
The organizing committee of FAAVSP 2015 is looking forward to your submissions.
We are pleased to announce the first call for papers for the sixth Workshop on Speech and Language Processing for Assistive Technologies (SLPAT) on Friday 11 September 2015 to be co-located with Interspeech 2015, Dresden, Germany. Full details on the workshop, topics of interest, timeline, and formatting of regular papers are here:
This workshop will bring together researchers from all areas of speech and language technology with a common interest in making everyday life more accessible for people with physical, cognitive, sensory, emotional, or developmental disabilities. The workshop will provide an opportunity for individuals from both research communities, and the individuals with whom they are working, to assist to share research findings, and to discuss present and future challenges and the potential for collaboration and progress. General topics include but are not limited to:
• Speech synthesis and speech recognition for physical or cognitive impairments
• Speech transformation for improved intelligibility
• Speech and language technologies for daily assisted living and Ambient Assisted Living (AAL)
• Translation systems; to and from speech, text, symbols and sign language
• Novel modeling and machine learning approaches for Augmentative and Alternative Communication (AAC) / Assistive Technologies (AT) applications
• Text processing for improved comprehension, e.g., sentence simplification or TTS
• Silent speech: speech technology based on sensors without audio
• Symbol languages, sign languages, nonverbal communication
• Dialogue systems and natural language generation for assistive technologies
• Multimodal user interfaces and dialogue systems adapted to assistive technologies
• NLP for cognitive assistance applications
• Presentation of graphical information for people with visual impairments
• Speech and NLP applied to typing interface applications
• Brain-computer interfaces for language processing applications
• Speech, natural language and multimodal interfaces to assistive technologies
• Assessment of speech and language processing within the context of AT
• Web accessibility; text simplification, summarization, and adapted presentation modes such as speech, signs or symbols
• Deployment of speech and NLP tools in the clinic or in the field
• Linguistic resources; corpora and annotation schemes
• Evaluation of systems and components, including methodology
(2015-09-12) Errors by Humans and Machines in multimedia, multimodal and multilingual data processing – ERRARE 2015, Sinaia (Romania)
Errors by Humans and Machines in multimedia, multimodal and multilingual data processing – ERRARE 2015
12-13 September 2015, Sinaia (Romania)
The Research Institute for Artificial Intelligence “Mihai Draganescu” (ICIA) of the Romanian Academy in collaboration with IMMI-CNRS, LIMSI-CNRS and the LAbEx EFL organizes the second edition of the “Errare” workshop, in September 12-13, 2015, as a satellite event of Interspeech 2015 (http://interspeech2015.org/).
The workshop will be organized around the topic of errors produced and processed by humans and machines in multimedia, multimodal and multilingual data with a particular focus on spoken language. It distinguishes itself from other conferences addressing these issues by providing a forum for dialogue and exchange between researchers working in linguistics, including psycho- and neurolinguistics, on the one hand, and researchers in computer science, machine learning and multimedia speech and language processing, on the other hand. For this interdisciplinary workshop, we would like to gather these different communities around the issues of variation, ambiguity and errors in speech and language. The purpose of this workshop is to share interdisciplinary expertise on a heterogeneous phenomenon referred to as “variation” and “ambiguity” in some domains and as “errors” in others. Researchers are invited to share their thoughts and observations through case studies run in the context of various initiatives.
A large panel of research areas shares a common object of study: human language. These areas encompass historically well-established research communities: classical humanities and social sciences (phonetics, phonology, psycholinguistics, etc.), and more recent domains of the sciences (brain and computer science). Research objectives include analyzing, modeling, understanding and theorizing the human processing of speech variation. For linguists and psycholinguists variation in speech involves some matching process between variable surface forms and stable underlying forms: in such a framework errors may naturally arise as mismatches occurring at the interface of surface and underlying representations. Yet by which mechanisms errors may arise and how to interpret the patterning of errors within theoretical models of speech production and perception has been a matter of controversy. Speech error research in recent years has particularly highlighted the fuzzy boundary between the concepts of 'variability', ambiguity' and 'error'. Research activities most often include corpora consisting of various types of recorded speech from controlled (laboratory) speech to large scale data. Such corpora may be a result of a variety of capturing techniques from standard audio recordings to multi-sensor capturing of either articulation gestures or brain activities. Errors can also be envisioned as a result of noisy data capturing conditions.
Sharing experience with errors, variation and ambiguity is expected to produce beneficial insights for the different communities:
Concerning humanities, variation and ambiguity are central to the different branches of linguistics. Furthermore, human production and perception errors challenge the existing language acquisition, production and perception models.
For automatic speech and language processing, residual errors indicate regions which escape current modeling capacities. In-depth analyses in collaboration with linguists, psycholinguists and speech scientists may contribute to a better understanding of these phenomena and to the proposal of innovative strategies.
Brain sciences, a recent rapidly evolving research area, open new opportunities and the study of errors can contribute to reveal the hidden organization of the brain.
We invite contributions focusing on errors produced by humans and/or machines from (but not limited to) the following areas:
Cognition and brain studies related to errors in speech Speech production (e.g. slips of the tongue...) Speech perception First and second language acquisition Bilingualism and code switching Voice pathologies / clinical phonetics Prosody Natural language processing Corpus linguistics Automatic speech processing Speech and multimodality Speech and language translation Spoken Interaction Information retrieval Evaluation methods
“Errare 2015” will welcome about 80 participants, with both invited and submitted papers.
Important dates: 27 April 2015: submission deadline 15 June 2015 : notifications of acceptance 29 June 2015 : final papers Workshop dates : 12-13 September 2015
Organizing committee: Ioana Vasilescu (LIMSI-CNRS) Gilles Adda (IMMI-LIMSI) Joseph Mariani (IMMI-LIMSI) Verginica Mititelu (ICIA, Romanian Academy) Dan Tufis (ICIA, Romanian Academy) Maria Candea (Un iversity Paris 3) Ioana Chitoran (University Paris 7) Sophie Rosset (LIMSI-CNRS) Guillaume Wisniewski (LIMSI-CNRS) Laurence Devillers (University Paris 4/LIMSI) Program committee: Gilles Adda (IMMI-LIMSI) Martine Adda-Decker (University Paris 3/LIMSI) Tiberiu Boros (ICIA, Romanian Academy) Maria Candea (University Paris 3) Ioana Chitoran (University Paris 7) Laurence Devillers (University Paris 4/LIMSI) Mirjam Ernestus (Radboud University & Max Planck Institute for Psycholinguistics) Julia Hirschberg (Columbia University) Lori Lamel (LIMSI-CNRS) Mark Liberman (University of Pennsylvania) Joseph Mariani (IMMI-LIMSI) Verginica Mititelu (ICIA, Romanian Academy) Bernd T. Meyer (Carl von Ossietzky Universität Oldenburg) Marianne Pouplier (Institut für Phonetik und Sprachverarbeitung Munchen) Sophie Rosset (LIMSI-CNRS) Dan Tufis (ICIA, Romanian Academy) Ioana Vasilescu (LIMSI-CNRS) Guillaume Wisniewski (LIMSI-CNRS)
(2015-09-14) CfP Eighteenth International Conference on TEXT, SPEECH and DIALOGUE (TSD 2015), Pilzen, Czech Republic
TSD 2015 - FIRST CALL FOR PAPERS **************************************************************************
Eighteenth International Conference on TEXT, SPEECH and DIALOGUE (TSD 2015) Plzen (Pilsen), Czech Republic, 14-17 September 2015 http://www.tsdconference.org
TSD HIGHLIGHTS
* Keynote speakers: Hermann Ney, Dan Roth, Björn W. Schuller, Peter D. Turney, and Alexander Waibel. * TSD is traditionally published by Springer-Verlag and regularly listed in all major citation databases: Thomson Reuters Conference Proceedings Citation Index, DBLP, SCOPUS, EI, INSPEC, COMPENDEX, etc. * TSD offers high-standard transparent review process - double blind, final reviewers discussion. * TSD is officially recognized as an INTERSPEECH 2015 satellite event. * TSD will take place in Pilsen, the European Capital of Culture 2015. * TSD provides an all-service package (conference access and material, all meals, one social event, etc) for an easily affordable fee starting at 270 EUR for students and 330 EUR for full participants.
IMPORTANT DATES
March 31, 2015 ............ Submission of full papers May 10, 2015 .............. Notification of acceptance May 31, 2015 .............. Final papers (camera ready) and registration
September 14-17, 2015 ....... Conference date
TSD SERIES
TSD series have evolved as a prime forum for interaction between researchers in both spoken and written language processing from all over the world. Proceedings of TSD form a book published by Springer-Verlag in their Lecture Notes in Artificial Intelligence (LNAI) series. The TSD proceedings are regularly indexed by Thomson Reuters Conference Proceedings Citation Index. LNAI series are listed in all major citation databases such as DBLP, SCOPUS, EI, INSPEC, or COMPENDEX.
The contributions to the conference will be published in proceedings that will be made available on a CD to participants at the time of the conference.
TOPICS
Keynote topic: Challenges of Modern Era in Speech and Language Processing
Topics of the conference will include (but are not limited to):
Corpora and Language Resources (monolingual, multilingual, text and spoken corpora, large web corpora, disambiguation, specialized lexicons, dictionaries)
Speech Recognition (multilingual, continuous, emotional speech, handicapped speaker, out-of-vocabulary words, alternative way of feature extraction, new models for acoustic and language modelling)
Tagging, Classification and Parsing of Text and Speech (multilingual processing, sentiment analysis, credibility analysis, automatic text labeling, summarization, authorship attribution)
Speech and Spoken Language Generation (multilingual, high fidelity speech synthesis, computer singing)
Semantic Processing of Text and Speech (information extraction, information retrieval, data mining, semantic web, knowledge representation, inference, ontologies, sense disambiguation, plagiarism detection)
Integrating Applications of Text and Speech Processing (machine translation, natural language understanding, question-answering strategies, assistive technologies)
Automatic Dialogue Systems (self-learning, multilingual, question-answering systems, dialogue strategies, prosody in dialogues)
Multimodal Techniques and Modelling (video processing, facial animation, visual speech synthesis, user modelling, emotions and personality modelling)
PROGRAM COMMITTEE
Elmar Noeth, Germany (general chair) Eneko Agirre, Spain Genevieve Baudoin, France Vladimir Benko, Slovakia Paul Cook, Australia Jan Cernocky, Czech Republic Simon Dobrisek, Slovenia Kamil Ekstein, Czech Republic Karina Evgrafova, Russia Darja Fiser, Slovenia Eleni Galiotou, Greece Radovan Garabik, Slovakia Alexander Gelbukh, Mexico Louise Guthrie, United Kingdom Jan Hajic, Czech Republic Eva Hajicova, Czech Republic Yannis Haralambous, France Hynek Hermansky, USA Jaroslava Hlavacova, Czech Republic Ales Horak, Czech Republic Eduard Hovy, USA Maria Khokhlova, Russia Daniil Kocharov, Russia Miloslav Konopik, Czech Republic Ivan Kopecek, Czech Republic Valia Kordoni, Germany Siegfried Kunzmann, Germany Natalija Loukachevitch, Russia Bernardo Magnini, Italy Vaclav Matousek, Czech Republic France Mihelic, Slovenia Roman Moucek, Czech Republic Hermann Ney, Germany Karel Oliva, Czech Republic Karel Pala, Czech Republic Nikola Pavesic, Slovenia Maciej Piasecki, Poland Adam Przepiorkowski, Poland Josef Psutka, Czech Republic James Pustejovsky, USA German Rigau, Spain Leon Rothkrantz, The Netherlands Anna Rumshisky, USA Milan Rusko, Slovakia Mykola Sazhok, Ukraine Pavel Skrelin, Russia Pavel Smrz, Czech Republic Petr Sojka, Czech Republic Stefan Steidl, Germany Georg Stemmer, Germany Marko Tadic, Croatia Tamas Varadi, Hungary Zygmunt Vetulani, Poland Pascal Wiggers, The Netherlands Yorick Wilks, United Kingdom Marcin Wolinski, Poland Victor Zakharov, Russia
OFFICIAL LANGUAGE
The official language of the event will be English. However, papers on processing of languages other than English are strongly encouraged.
CONFERENCE FEES
The conference fee depends on the date of payment and on your status. It includes one copy of the conference proceedings, refreshments/coffee breaks, opening dinner, welcome party, mid-conference social event admissions, and organizing costs. In order to lower the fee as much as possible, the accommodation and the conference trip are not included.
Full participant: early registration by May 31, 2015 - CZK 9.000 (approx. 330 EUR) late registration by August 1, 2015 - CZK 10.000 (approx. 370 EUR) on-site registration - CZK 10.700 (approx. 390 EUR)
Student (reduced): early registration by May 31, 2015 - CZK 7.400 (approx. 270 EUR) late registration by August 1, 2015 - CZK 9.000 (approx. 330 EUR) on-site registration - CZK 10.000 (approx. 370 EUR)
LOCATION
The city of Plzeň (Pilsen) is situated in Western Bohemia at the confluence of four rivers. With its 170,000 inhabitants it is the fourth largest city in the Czech Republic and an important industrial, commercial, and administrative centre. It is also the capital of the Pilsen Region. In addition, Pilsen won the title of the European Capital of Culture for the upcoming year 2015.
Pilsen is well-known for its brewing tradition. The trademark Pilsner-Urquell has a good reputation all over the world thanks to the traditional recipe, high quality hops and good groundwater. Beer lovers will also appreciate a visit to the Brewery Museum or the Brewery itself.
Apart from its delicious beer, Pilsen hides lots of treasures in its core. The city can boast the second largest synagogue in Europe. The dominant of the old part of the city center is definitely the 13th-century Gothic cathedral featuring the highest church tower in Bohemia (102.34 m). It is possible to go up and admire the view of the city. Not far from the cathedral is the splendid Renaissance Town Hall from 1558 and plenty of pleasant cafes and pubs are situated on and around the main square.
There is also the beautiful Pilsen Historical Underground - under the city center, a complex network of passageways and cellars can be found. They are about 14 km long and visitors can see the most beautiful part of this labyrinth during the tour. It is recommended to visit the City Zoological Garden, having the second largest space for bears in Europe and keeping several Komodo dragons, large lizards which exist only in a few zoos in the world.
The University of West Bohemia in Pilsen provides a variety of courses for both Czech and international students. It is the only institution of higher education in this part of the country which prepares students for careers in engineering (electrical and mechanical), science (computer science, applied mathematics, physics, and mechanics), education (both primary and secondary), economics, philosophy, politics, archeology, anthropology, foreign languages, law and public administration, art and design.
ABOUT CONFERENCE
The conference is organized by the Faculty of Applied Sciences, University of West Bohemia, Pilsen, and the Faculty of Informatics, Masaryk University, Brno. The conference is supported by International Speech Communication Association (ISCA).
Venue: Plzeň (Pilsen), Parkhotel Congress Center Plzeň, Czech Republic
ADDRESS
All correspondence regarding the conference should be addressed to: Ms Anna Habernalová, TSD2015 Conference Secretary E-mail: tsd2015@tsdconference.org Phone: (+420) 724 910 148 Fax: +420 377 632 402 - Please, mark the faxed material with capitals 'TSD' on top. TSD 2015 conference web site: http://www.tsdconference.org/tsd2015
The SoA conferences have brought together, for the past 15 years, senior and junior scientists working in the multidisciplinary field of Neurocognition of language and deal with normal function as well as disorders. The conference structure ensures direct and informal interaction between all participants.
The conference program will include keynotes (mornings), and contributed oral and poster presentations (afternoons) over 4 days (between the 18th and the 21st of September 2015). Full/student registration will include the conference proceedings, lunches, coffee breaks, a social program and conference dinner. Participants will be able to register only for a day as well.
Abstracts can be submitted at http://www.soa-online.com/submission/ until the 1st of April. Selected abstract authors will then be invited to submit full length papers.
Conference proceeding will be published as part of a special number of the journal Stem-, Spraak- en Taalpathologi. The papers are published online at the journal's website (see previous conference proceedings here) and a printed copy is distributed to all conference participants.
The venue is the School of Health Sciences at University of Aveiro's Campus de Santiago, overlooking the Aveiro's lagoon, which is renowned internationally for its many buildings designed by famous Portuguese architects, only at a short distance from the city centre (5 minute walk).
SIGDAT, the Association for Computational Linguistics' special interest group on linguistic data and corpus-based approaches to NLP, invites submissions to EMNLP 2015.
The conference will be held on September 17-21 2015 in Lisbon, Portugal. The conference will consist of three days of full paper presentations with two days of workshops and tutorials.
Conference URL: http://www.emnlp2015.org
The conference web site will include updated information on workshops, tutorials, venue, traveling, etc. For helpful tips on visiting Lisbon, Portugal, please check the WikiTravel website
(http://wikitravel.org/en/Lisboa).
As in recent years, some of the presentations at the conference will be of papers accepted for the Transactions of the ACL journal (http://www.transacl.org/).
WORKSHOPS & TUTORIALS
EMNLP 2015 will have a large workshop program with 7 workshops and 8 tutorials. See http://www.emnlp2015.org/workshops.html and http://www.emnlp2015.org/tutorials.html for more details.
TOPICS
We solicit papers on all areas of interest to the SIGDAT community and aligned fields, including but not limited to:
- Phonology, Morphology, and Segmentation
- Tagging, Chunking, Parsing and Syntax
- Discourse, Dialogue, and Pragmatics
- Semantics
- Summarization and Generation
- Statistical Models and Machine Learning Methods
- Machine Translation and Multilinguality
- Information Extraction
- Information Retrieval and Question Answering
- Sentiment Analysis and Opinion Mining
- Spoken Language Processing
- Computational Psycholinguistics
- NLP for Web and Social Media (including Computational Social Science)
- Language and Vision
- Text Mining and NLP Applications
IMPORTANT DATES
- Long Paper submission deadline: May 31, 2015
- Short Paper submission deadline: June 15, 2015
- Author response period: July 7-10, 2015
- Acceptance notification: July 24, 2015
- Camera-ready submission deadline: August 14, 2015
- Workshops and tutorials: September 17-18, 2015
- Main conference: September 19-21, 2015
All deadlines are calculated at 11:59pm (UTC/GMT -11 hours)
SUBMISSIONS
Long papers
EMNLP 2015 submissions must describe substantial, original, completed and unpublished work. Wherever appropriate, concrete evaluation and analysis should be included. Each submission will be reviewed by at least three program committee members.
Each long paper submission consists of a paper of up to eight (8) pages of content, plus two pages for references; final versions of long papers will be given one additional page (up to 9 pages with 2 pages for references) so that reviewers' comments can be taken into account.
Short papers
EMNLP 2015 also solicits short papers. Short paper submissions must describe original and unpublished work. While a short paper is not a shortened long paper, the characteristics of short papers include:
- A small, focused contribution
- Work in progress
- A negative result
- An opinion piece
- An interesting application nugget
Each short paper submission consists of up to four (4) pages of content, plus 2 pages for references. Upon acceptance, short papers will be given five (5) pages in the proceedings and 2 pages for references. Authors are encouraged to use this additional page to address reviewers' comments in their final versions. Each short paper submission will be reviewed by at least three program committee members.
Both long and short papers
Papers may be accompanied by the resources (software and/or data) described in the papers. Papers that are submitted with accompanying software/data may receive additional credit toward the overall evaluation score, and the potential impact of the software and data will be taken into account when making the acceptance/rejection decisions.
Accepted papers will be presented orally or as a poster (at the discretion of the program chairs). There will be no distinction in the proceedings between papers presented orally or as posters.
Both long and short papers should follow the two-column format to be provided at the conference site. We reserve the right to reject submissions if the paper does not conform to these styles, including paper size and font size restrictions.
As the reviewing will be blind, papers should not include the authors' names and affiliations. Furthermore, self-references that reveal the author's identity, e.g., “We previously showed (Smith, 1991) ...‚”, should be avoided. Instead, use citations such as‚ ”Smith (1991) previously showed ...‚”. Submissions that do not conform to these requirements will be rejected without review. Separate author identification information is required as part of the on-line submission process.
Submission will be online, managed by the START system (https://www.softconf.com/emnlp2015/papers). The site will be open for accepting submissions one and half months before the conference deadline. To minimize network congestion we request authors upload their submissions as early as possible.
EMNLP multiple submission policy
Papers that have been or will be submitted to other meetings or publications must indicate this at submission time, and must be withdrawn from the other venues if accepted by EMNLP 2015. We will not accept for publication or presentation papers that overlap significantly in content or results with papers that will be (or have been) published elsewhere.
Authors submitting more than one paper to EMNLP 2015 must ensure that submissions do not overlap significantly (>25%) with each other in content or results.
Preprint servers such as arXiv.org and ACL-related workshops that do not have published proceedings in the ACL Anthology are not considered archival for purposes of submission. Authors must state in the online submission form the name of the workshop or preprint server and title of the non-archival version. The submitted version should be suitably anonymized and not contain references to the prior non-archival version. Reviewers will be told: 'The author(s) have notified us that there exists a non-archival previous version of this paper with significantly overlapping text. We have approved submission under these circumstances, but to preserve the spirit of blind review, the current submission does not reference the non-archival version.' Reviewers are free to do what they like with this information.
PRESENTATION REQUIREMENT
All accepted papers must be presented at the conference to appear in the proceedings. At least one author of each accepted paper must register for EMNLP 2015.
ORGANIZING COMMITTEE
General Chair
Lluís Márquez, Qatar Computing Research Institute
Program co-Chairs
Chris Callison-Burch, University of Pennsylvania
Jian Su, Institute for Infocomm Research (I2R)
Workshops co-Chairs
Zornitsa Kozareva, Yahoo! Labs
Jörg Tiedemann, Uppsala University
Tutorial co-Chairs
Maggie Li, Hong Kong Polytechnic University
Khalil Sima'an, University of Amsterdam
Publication co-Chairs
Daniele Pighin, Google Inc.
Yuval Marton, Microsoft Corp.
Publicity Chair
Barbara Plank, University of Copenhagen
Sponsorship Team
Hang Li, Huawei Technologies
João Graça, Unbabel Inc.
SIGDAT Liaison
Noah Smith, Carnegie Mellon University
Local co-Chairs
André Martins, Priberam
João Graça, Unbabel Inc.
Local Publicity Chair
Isabel Trancoso, University of Lisbon
Conference Handbook Chair
Fernando Batista, University Institute of Lisbon (ISCTE-IUL)
(2015-09-20) 17th International Conference on Speech and Computer (SPECOM 2015), Athens, Greece
SPECOM 2015 - CALL FOR PAPERS *********************************************************
17th International Conference on Speech and Computer (SPECOM 2015) Venue: Athens, Greece, September 20-24, 2015 Web: http://specom.nw.ru
ORGANIZERS
The conference is organized by University of Patras (Patras, Greece), in cooperation with Moscow State Linguistic University (MSLU, Moscow, Russia) and St. Petersburg Institute for Informatics and Automation of the Russian Academy of Science (SPIIRAS, St. Petersburg, Russia).
SPECOM conferences
Ten years later the SPECOM conference returns to Greece. Recently SPECOM venue is significantly varied: Patras, Greece, 2005; St.Petersburg, Russia, 2006; Moscow, Russia, 2007; St.Petersburg, Russia, 2009; Kazan, Russia, 2011; Plzen, Czech Republic, 2013; Novi Sad, Serbia, 2014. The last conferences were organized in parallel with TSD'2013 and DOGS'2014 and had a great success and benefits of joining the various research teams. SPECOM Proceedings will be published by Springer-Verlag as a book in the Lecture Notes in Artificial Intelligence (LNAI) series listed in all major citation databases such as DBLP, SCOPUS, EI, INSPEC, COMPENDEX. SPECOM Proceedings are included in the list of forthcoming proceedings for September 2015.
TOPICS
The SPECOM conference is devoted to issues of human-machine interaction, particullly: Applications for human-computer interaction Audio-visual speech processing Automatic language identification Corpus linguistics and linguistic processing Forensic speech investigations and security systems Ðuman-robot interaction Multichannel signal processing Multimedia processing Multimodal analysis and synthesis Signal processing and feature extraction Speaker identification and diarization Speaker verification systems Speech and language resources Speech driving systems in robotics Speech enhancement Speech perception and speech disorders Speech recognition and understanding Speech translation automatic systems Spoken dialogue systems Spoken language processing Text-to-speech and Speech-to-text systems
OFFICIAL LANGUAGE
The official language of the event will be English. However, papers on processing of languages other than English are strongly encouraged.
PROGRAMME COMMITTEE
Etienne Barnard, North-West University, South Africa Laurent Besacier, Laboratory of Informatics of Grenoble, France Vlado Delic, University of Novi Sad, Serbia Christoph Draxler, Institute of Phonetics and Speech Communication, Germany Thierry Dutoit, University of Mons, Belgium Nikos Fakotakis, University of Patras, Greece Peter French, University of York, UK Hiroya Fujisaki, University of Tokyo, Japan Slobodan Jovicic, University of Belgrade, Serbia Ruediger Hoffmann, Dresden University of Technology, Germany Dimitri Kanevsky, IBM Thomas J. Watson Research Center, USA Alexey Karpov, SPIIRAS, Saint-Petersburg, Russia Walter Kellerman, Erlangen-Nurnberg University, Germany George Kokkinakis, University of Patras, Greece Steven Krauwer, Utrecht University, The Netherlands Lin-shan Lee, National Taiwan University, Taiwan Boris Lobanov, United Institute of Informatics Problems, Belarus Benoit Macq, University Сatholique de Louvain, Belgium Roger Moore, Sheffield University, UK Yuri Matveev, ITMO University, Russia Geza Nemeth, Budapest University of Technology and Economics, Hungary Heinrich Niemann, University of Erlangen-Nuremberg, Germany Alexander Petrovsky, Belarusian State University of Informatics and Radioelectronics, Belarus Rodmonga Potapova, Moscow State Linguistic University, Russia Dimitar Popov, Bologna University, Italy Lawrence Rabiner, Rutgers University, USA Gerhard Rigoll, Munich University of Technology, Germany Andrey Ronzhin, SPIIRAS, Saint-Petersburg, Russia Murat Saraclar, Bogazici University, Turkey Jesus Savage, University of Mexico, Mexico Tanja Schultz, University of Karlsruhe, Germany Milan Secujski, University of Novi Sad, Serbia Pavel Skrelin, St. Petersburg State University, Russia Viktor Sorokin, Institute for Information Transmission Problems, Russia Yannis Stylianou, University of Crete, Greece Christian Wellekens, EURECOM, France Milos Zelezny, University of West Bohemia, Czech Republic
FORMAT OF THE CONFERENCE
The conference program will include presentation of invited papers, oral presentations, and poster/demonstration sessions. Papers will be presented in plenary or topic oriented sessions. Details about the social events will be available on the web page.
SUBMISSION OF PAPERS
Authors are invited to submit a full paper not exceeding 8 pages formatted in the LNCS style (see below). Those accepted will be presented either orally or as posters. The decision on the presentation format will be based upon the recommendation of three independent reviewers. The authors are asked to submit their papers using the on-line submission form accessible from the conference web site. Papers submitted to SPECOM 2015 must not be under review by any other conference or publication during the SPECOM review cycle, and must not be previously published or accepted for publication elsewhere. As the reviewing is blind, the paper should not include authors' names and affiliations.
IMPORTANT DATES
April 15, 2015 ............ Submission of full papers June 01, 2015 ............ Notification of acceptance June 15, 2015 ............ Final papers (camera ready) and registration
September 20-24, 2015 ........ Conference date
The contributions to the conference will be published in proceedings that will be made available to participants at the time of the conference.
CONFERENCE FEES
The conference fee depends on the date of payment and on your status. It includes one copy of the conference proceedings, refreshments/coffee breaks, opening dinner, welcome party, mid-conference social event admissions, and organizing costs. In order to lower the fee as much as possible, meals during the conference, the accommodation, and the conference trip are not included.
Full participant: early registration by June 15, 2015 – 380 EUR late registration by August 20, 2015 – 420 EUR on-site registration – 470 EUR
Student (reduced): early registration by June 15, 2015 – 300 EUR late registration by August 20, 2015 – 330 EUR on-site registration – 370 EUR
The payment may be refunded up until August 20, at the cost of 60 EUR. No refund is possible after this date. At least one of the authors has to register and pay the registration fee by June 15, 2015 for their paper to be included in the conference proceedings. Only one paper of up to 8 pages is included in the regular registration fee. An author with more than one paper pays the additional paper rates unless a co-author has also registered and paid the full registration fee. In the case of uncertainty, feel free to contact the organising committee for clarification.
VENUE
The conference will be organized in Athens, Greece. Each year, more and more travelers are choosing Athens for their leisure and business travel all year round. Athens offers a variety of things to see and do, and most of the times, under favorable weather conditions. Athens is considered one of Europe's safest capitals; its transportation network is user-friendly; there are numerous museums and archeological sites and hundreds of restaurants to satisfy every taste.
CONTACTS
All correspondence regarding the conference should be addressed to: SPECOM Secretariat E-mail: specom@iias.spb.su Phone/Fax: +7 812 328 7081 Fax: +7 812 328 4450 — Please, designate the faxed material with capitals 'SPECOM' on top. SPECOM 2015 conference web site: www.specom.nw.ru
(2015-09-28) 57th International Symposium ELMAR-2015 , Zadar, Croatia
57th International Symposium ELMAR-2015 *************************************** September 28-30, 2015 Zadar, Croatia Paper submission deadline: March 25, 2015
http://www.elmar-zadar.org/ CALL FOR PAPERS TOPICS --> Image and Video Processing --> Multimedia Communications --> Speech and Audio Processing --> Wireless Communications --> Telecommunications --> Antennas and Propagation --> e-Learning and m-Learning --> Navigation Systems --> Ship Electronic Systems --> Power Electronics and Automation --> Naval Architecture --> Sea Ecology --> Special Sessions: http://www.elmar-zadar.org/2015/special_sessions/ SCHEDULE OF IMPORTANT DATES Deadline for submission of full papers: March 25, 2015 Notification of acceptance mailed out by: May 6, 2015 Submission of (final) camera-ready papers: June 3, 2015 Preliminary program available online by: June 17, 2015 Registration forms and payment deadline: June 17, 2015
(2015-09-xx) MultiLing 2015:Multilingual Summarization of Multiple Documents, Online Fora and Call Centre Conversations, Prague, Czech Republic
= Call for Participation =
= MultiLing 2015: Multilingual Summarization of Multiple Documents, Online Fora and Call Centre Conversations =
= Introduction =
From Caesar's `Veni, Vidi, Vici' to `What might be in a summary?' (Karen Sparck-Jones, 1993) summarization techniques have been key to successfully grasping the main points of large amounts of information, and much research has been devoted to improving such techniques. In the past two decades, the progress of summarization research has been supported by evaluation exercises and shared tasks such as DUC, TAC and, more recently, MultiLing (2011, 2013). Multiling is a community-driven initiative for benchmarking multilingual summarization systems, nurturing further research, and pushing the state-of-the-art in the area. The aim of MultiLing 2015 is to continue this evolution and, in addition, to introduce new tasks promoting research on summarizing free human interaction in online fora and customer call centres. With this call we wish to invite the summarization research community to participate in MultiLing 2015.
= The Tasks =
MultiLing 2015 will feature the Multilingual Multi-document Summarization task familiar from previous editions and its predecessor, the Multilingual Single-document Summarization. In addition, we will pilot two new tracks, Online Forum Summarization (OnForumS) and Call Centre Conversation Summarization (CCCS), in collaboration with the SENSEI EU project (http://www.sensei-conversation.eu). We describe each task in turn below.
The multilingual multi-document summarization track aims to evaluate the application of (partially or fully) language-independent summarization algorithms on a variety of languages. Each system participating in the track will be called to provide summaries for a range of different languages, based on a news corpus. Participating systems will be required to apply their methods to a minimum of two languages. Evaluation will favor systems that apply their methods to more languages.
The corpus used in the Multilingual multi-document summarization track will be based on WikiNews texts (http://www.wikinews.org/). Source texts will be UTF-8, clean texts (without any mark-up, images,etc.).
The task requires systems to generate a single, fluent, representative summary from a set of documents describing an event sequence. The language of the document set will be within a given range of languages and all documents in a set share the same language. The output summary should be of the same language as its source documents. The output summary should be 250 words at most.
Following the pilot task of 2013, the multi-lingual single-document summarization task will be to generate a single document summary for all the given Wikipedia feature articles from one of about 40 languages provided. The provided training data will be the 2013 Single-Document Summarization Pilot Task data from MultiLing 2013. A new set of data will be generated based on additional Wikipedia feature articles. For each language 30 documents are given. The documents will be UTF-8 without mark-ups and images. For each document of the training set, the human-generated summary is provided. For MultiLing 2015 the character length of the human summary for each document will be provided, called the target length. Each machine summary should be as close to the target length provided as possible. For the purpose of evaluation all machine summaries greater than the target length will be truncated to the target length. The summaries will be evaluated via automatic methods and participants will be required to perform some limited summarization evaluations.
The manual evaluation will consist of pairwise comparisons of machine-generated summaries. Each evaluator will be presented the human-generated summary and two machine-generated summaries. The evaluation task is to read the human summary and then judge if the one machine-generated summary is significantly closer to the human generated summary information content (e.g. system A > system B or system B > system A) or if the two machine-generated summaries contain comparable quanties of information as the human-generated summary.
== Online Forum Summarization (OnForumS) ==
Most major on-line news publishers, such as The Guardian or Le Monde, publish articles on different topics and encourage reader engagement through the provision of an on-line comment facility. A given news article can often give rise to thousands of reader comments -- some related to specific points within the article, others that are replies to previous comments. The great volume of such user-supplied comments suggests the need for automated methods to summarize this content, which in turn poses an exciting and novel challenge for the summarization community.
The purpose of the Online Forum Summarization (OnForumS) track at MultiLing'15 is to set the ground for investigating how such a mass of comments can be summarised. We posit that a crucial initial step in developing reader comment summarization systems is to determine what comments relate to, be that either specific points within the text of the article, the global topic of the article, or comments made by other users. This constitutes a linking task. Furthermore, a set of link types or labels may be articulated to capture whether, for example, a comment agrees with, elaborates, disagrees with, etc., the point made in the commented-upon text. Solving this labelled linking problem should facilitate the creation of reader comment summaries by allowing, for example, that comments relating to the same article content can be clustered, points attracting the most comment can be identified, representative comments can be chosen for each key point, and the implications of labelled links can be digested (e.g., numbers for or against a particular point), etc.
The SMS task at MultiLing'15 is a particular specification of the linking task, in which systems will take as input a news article with a reduced set of comments (sifted, according to predefined criteria, from what could otherwise be thousands of comments) and are asked to link and label each comment to sentences in the article (which, for simplification, are assumed to be the appropriate units here), to the article topic as a whole, or to preceding comments. Precise guidelines for when to link and for the link types, will be released as part of the formal task specification, but we anticipate the condition for linking will require sentences addressing the same assertion, and that link types will include at least agreement, disagreement, and sentiment indicators. The data will cover at least three languages (English, Italian, and French); a small set of link-labelled articles will be provided by the SENSEI project for each of these languages for illustration and for development. Additional languages may be covered if the data for these are provided by the participants in the task. These data could be either translations of the data for other languages, or comparable articles *on the same topics*.
Evaluation will be based on the results of a crowd-sourcing exercise, in which crowd workers are asked to judge whether potential links, and associated labels, are correct for each given test article plus associated comments.
== Call Centre Conversation Summarization (CCCS) ==
Speech summarization has been of great interest to the community because speech is the principal modality of human communications and it is not as easy to skim, search or browse speech transcripts as it is for textual messages. Speech recorded from call centers offers a great opportunity to study goal-oriented and focused conversations between an agent and a caller. The Call Centre Conversation Summarization (CCCS) task consists in automatically generating summaries of spoken conversations in the form of textual synopses that shall inform on the content of a conversation and might be used for browsing a large database of recordings. Compared to news summarization where extractive approaches have been very successful, the CCCS task's objective is to foster work on abstractive summarization in order to depict what happened in a conversation instead of what people actually said.
The MultiLing'15 CCCS track leverages conversations from the DECODA and LUNA corpora of French and Italian call center recordings, both with transcripts available in their original language as well as English translation (both manual and automatic). Recording duration range from a few minutes to 15 minutes, involving two or sometimes more speakers. In the public transportation and help desk domains, the dialogs offer a rich range of situations (with emotions such as anger or frustration) while staying in a coherent domain.
Given transcripts, participants to the task shall generate abstractive summaries informing a reader about the main events of the conversations, such as the objective of the caller, whether and how it was solved by the agent, and the attitude of both parties. Evaluation will be performed by comparing submissions to reference synopses written by experts. Both conversations and reference summaries are kindly provided by the SENSEI project.
= Roadmap = Finalization pending. (PLEASE PROVIDE FEEDBACK on the submission dates, if you plan to participate, by e-mailing: ggianna AT iit DOT demokritos DOT gr.)
* Training data ready: (date to be finalized per task) Dec 12th, 2014 * Test data available: Feb 15th, 2015 * System submissions due: Feb 28th, 2015 * Evaluation starts: Mar 1st, 2015 * Evaluation ends: Mar 31st, 2015 * Paper submission due: May 1st, 2015 * Paper reviews due: May 15th, 2015 * Camera-ready due: Jun 15th, 2015 * Workshop: 1st week of Sep , 2015
= Program Committee Members = (Full list of PC members pending)
The Program Committee members are: George Giannakopoulos - NCSR Demokritos (overall chair, MMS Task chair) Jeff Kubina, John Conroy - IDA Center for Computing Sciences (MSS Task chairs) Mijail Kabadjov - University of Essex (OnForumS Task co-chair) Josef Steinberger - University of West Bohemia, Czech Republic (OnForumS Task co-chair) Benoit Favre - University of Marseille (CCCS Task co-chair) Udo Kruschwitz and Massimo Poesio - University of Essex Emma Barker, Rob Gaizauskas and Mark Hepple - University of Sheffield Vangelis Karkaletsis - NCSR Demokritos Fabio Celli - University of Trento
Data Contributors (from MultiLing 2013) =========================================== Georgios Petasis, George Giannakopoulos - NCSR 'Demokritos', Greece Josef Steinberger - University of West Bohemia, Czech Republic Mahmoud El-Haj - Lancaster University, UK Ahmad Alharthi - King Saud University, Saudi Arabia Maha Althobaiti - Essex University, UK Corina Forascu - Romanian Academy Research Institute for Artificial Intelligence (RACAI), and Alexandru Ioan Cuza University of Iasi (UAIC), Romania Jeff Kubina, John Conroy, Judith Shleshinger - IDA/Center for Computing Sciences, USA Lei Li - Beijing University of Posts and Telecommunications (BUPT), China Marina Litvak - Sami Shamoon College of Engineering, Israel Sabino Miranda - Center for Computing Research, Instituto Politécnico Nacional, Mexico
The aim of this 9th edition is to bring together researchers interested in the notion of the trace, from theoretical and methodological perspective in various disciplines. The term trace raises both by its multiple meanings and by its recurring presence in the scientific literature. While trace is a common term used in everyday language, the apparent straightforwardness of its meaning hides a number of complex questions in the literature about the contextualization of the term. These questions are all the more relevant in the digital age where the trace is playing an increasingly important role in IT environments (review Intellectica, No. 59). To begin with, an epistemological questioning calls for a multidisciplinary approach. In 2002, A. Serres drew up an inventory of possible meanings of the term trace (as a marker, as an clue) and discussed its presence in literature, linguistics and philosophy. His approach constitutes a solid basis for our thinking. Serres also reviewed intrinsic links between trace and memory (Ricoeur) and trace and writing (Derrida). Secondly, this notion of trace is omnipresent in the field of Linguistics and can be found at all levels of research (epistemological, pragmatic and praxeological). Therefore, it is worth revisiting, at a methodological level, the practices of identification, creation, exploitation and conservation of objects of research, considered as traces of this research : what about the positioning and choices of young researchers on data collection, analysis of corpus, archiving ?
Phonetics and phonology: If we consider sound as a trace in the elastic medium represented by the air, it is worthwhile discussing the notion of the trace in relation to the acoustic signal. In fact, sound traces the acoustic signal thanks to the articulatory gestures. Those gestures can be altered by a communication disorder which will leave a number of traces in the speech. Finally, in the voice, other traces can be observed allowing one to identify the speaker’s gender or his/her emotions.
Language acquisition, didactics and language learning: In the learning process, the target language acquisition is based on existing knowledge and skills that will be progressively transferred from the source language. Therefore, various traces of the first language can be found in the second language, reflecting different levels of the language: linguistics, pragmatics or sociocultural.
Written communication: In the written communication, the participants are not in a situation of co-presence. Therefore, we can talk about a delayed communication that seems to be an interesting subject for discussion. Indeed, the written communication fits into the framework of elaboration and conservation of the traces. As this communication mode is not subject to the constraints that are tied up with the speech flow, it allows backtracking, corrections or erasing all of which may be studied by the researcher. Finally, the four basic operations of substitution (addition, removal, substitution and displacement) can also be detected thanks to their graphic traces.
Digital communication: When considering interactions within the computing environment, it is impossible not to include traces which result from the usage of these devices. Indeed, every user or machine profile leaves a binary line (internet identity). This binary line constitutes a form of digital writing which contributes to a synchronous and an asynchronous communication. This raises several questions related to the trace: its acquisition, its development, its visualization, its archiving, its annotation, its suppression and its recovery.
Language processing: Language processing is essential when it comes to make use of the trace, recover it, repair it or rebuild it. To intercept the trace, researchers create algorithmic models in the form of procedures using a software architecture that will run a program on one or more computers, on condition that those computers are connected together via social networks or internet. These models are developed with adjustable variables allowing to specify the task through the gathered trace. Therefore, we will be able to work with the trace: cut or label it, define its structure, evaluate its meaning, contextualize or generate it.
Contributions from the following areas of linguistics will be considered with the utmost attention: Syntax, Morphology, Semantics, Pragmatics, Phonetics, Phonology, Neurolinguistics, Psycholinguistics, Language Acquisition, TAL, etc. Proposals combining theoretical reflections and naturally occurring data will be particularly appreciated.
Submission: Submitted abstracts should be 800 words long (excluding references and tables). The deadline for our call for papers is March 31st 2015. Submissions must be made via EasyChair: https://easychair.org/conferences/?... Proposals will be reviewed anonymously by two members of the Scientific Committee. Notification of acceptance will be communicated in May.
Registration: Registration should be made via Azur Colloque : http://www.azur-colloque.cnrs.fr/
Fees: Standard registration – early : 70 EUR (on or before September 1st, 2015) Standard registration – regular : 80 EUR (after September 1st, 2015) Visitor registration – early : 80 EUR (on or before September 1st, 2015) Visitor registration – regular : 90 EUR (after September 1st, 2015)
Registration fees include: Access to all sessions / Coffee breaks / Lunch
(2015-10-18) 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA15), New Paltz, NY, USA
CALL FOR PAPERS 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA15) Mohonk Mountain House, New Paltz, New York October 18-21, 2015
Important Dates Submission of papers: April 10, 2015 Notification of acceptance: June 26, 2015 Early registration until: August 14, 2015 Workshop: October 18-21, 2015
The 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA?15) will be held at the Mohonk Mountain House in New Paltz, New York, and is supported by the Audio and Acoustic Signal Processing technical committee of the IEEE Signal Processing Society. The objective of this workshop is to provide an informal environment for the discussion of problems in audio and acoustics and signal processing techniques leading to novel solutions. Technical sessions will be scheduled throughout the day. Afternoons will be left free for informal meetings among workshop participants. Papers describing original research and new concepts are solicited for technical sessions on, but not limited to, the following topics:
Acoustic Signal Processing:
Source separation: Single- and multi-microphone techniques
Source localization
Signal enhancement: Dereverberation, noise reduction, echo reduction
Following the success of the 2011 and 2013 CHiME challenges it gives us great pleasure to pre-announce the 3rd CHiME Speech Separation and Recognition Challenge (CHiME-3)
CHiME-3 will be an official IEEE ASRU 2015 Challenge Task. Participants will be invited to submit CHiME-3 papers to the ASRU workshop to be held in Scottsdale, Arizona 13-17 December. Papers will be presented at a Special Session.
THE TASK
The CHiME-3 scenario will be ASR for a multi-microphone tablet device in everyday, noisy environments. It will represent a significant step forward in terms of both realism and difficulty with respect to the previous CHiME challenges.
The challenge will feature:
- 6-channel microphone array data, - real acoustic mixing, i.e. talkers speaking in challenging noisy environments, - varied noise settings including cafe, street junction, public transport.
To maintain compatibility with the 2nd CHiME challenge, the new challenge will re-use the WSJ evaluation framework. Utterances will be provided embedded in continuous audio with ground truth VAD annotations.
MATERIALS
At time of launch in February we will provide: - a development test set, recorded by 4 US talkers across 4 noise environments, - a real training set, comprised of 2000 utterances spoken by 4 US talkers in noisy environments plus several hours of noise background per environment, - tools for generating a simulated training set by remixing WSJ and background audio with impulse responses estimated from the real data, - a reference speech enhancement system and a state-of-the-art DNN-based Kaldi ASR system.
As with previous CHiME challenges we invite participation from both the signal processing and the speech recognition communities. To support teams who lack access to the necessary GPU infrastructure required to run the evaluation system, we will offer 'remote evaluation' as a service.
If you are considering participating please email chimechallenge@gmail.com and you will be added to the email list for receiving further updates.
IMPORTANT DATES
Feb 20, 2015 -- Launch - Training data + dev data release May 15, 2015 -- Test set released July 15, 2015 -- Challenge paper submission deadline September 11, 2015 -- Paper notification & release of CHiME-3 results December 13-17, 2015 -- ASRU Workshop
(2015-12-13) ASRU 2015 : IEEE Automatic Speech Recognition and Understanding Workshop, Scottsdale, AZ, USA
ASRU 2015 : IEEE Automatic Speech Recognition and Understanding Workshop
December 13-17, 2015 Scottsdale, Arizona, USA
http://asru2015.org
Twitter: @ASRU2015
CALL FOR PAPERS
The fourteenth biannual IEEE workshop on Automatic Speech Recognition and Understanding (ASRU) will be held on December 13-17, 2015 in Scottsdale, Arizona - USA. The ASRU workshop meets every two years and has a tradition of bringing together researchers from academia and industry in an intimate and collegial setting to discuss problems of common interest in automatic speech recognition, understanding, and related fields of research.
TOPICS AND FOCUS
Authors are encouraged to submit contributions in all areas of spoken language processing, with emphasis placed on the following topics:
- Automatic speech recognition
- Spoken language understanding
- Speech-to-text systems
- Spoken dialog systems
- Multilingual language processing
- Robustness in automatic speech recognition
- Spoken document retrieval
- Speech-to-speech translation
- Text-to-speech systems
- Spontaneous speech processing
- Speech summarization
- New applications of automatic speech recognition
FORMAT
The workshop features one keynote and one or two invited talks a day. Regular papers are presented as posters. See http://asru2015.org for formatting guidelines. ASRU 2015 will also include challenge tasks, panel discussions and demo sessions.
CHALLENGE TASKS
Three challenge tasks will be reporting results at ASRU 2015:
- 3rd CHiME Speech Separation and Recognition Challenge - http://spandh.dcs.shef.ac.uk/chime_challenge
- Automatic Speech recognition In Reverberant Environments (ASpIRE) - https://www.innocentive.com/ar/challenge/9933624
- Multi-genre Broadcast Media Transcription Challenge - http://www.mgb-challenge.org/
Papers related to the challenges will be submitted, reviewed, and evaluated in the same way as all ASRU papers. Accepted papers will be presented as posters in special sessions for each challenge task.
The challenges themselves are run by their respective organizers, independently of ASRU 2015. See http://asru2015.org/Challenges.asp for participation details.
PAPER SUBMISSION
Prospective authors are invited to submit full-length, 4-6 page papers, including figures, plus 1-2 additional pages for references only. All papers will be handled and reviewed electronically.
SCHEDULE
Paper due date: Friday July 10, 2015
Paper Notification: Friday Sept 11, 2015
Registration opens: Friday Sept 11, 2015
Demo/toolkit deadline: Friday Sept 25, 2015
Paper Camera ready version due: Friday Oct 2, 2015
Demo/toolkit notification date: Friday Oct 9, 2015
Author and early registration end: Friday Oct 23, 2015
Demo/toolkit camera ready version due: Monday Oct 26, 2015
Workshop: Dec 13-17, 2015
MORE INFORMATION
For updates see www.asru2015.org, or follow us on twitter: @ASRU2015
ASRU 2015 welcomes proposals for challenge tasks. In a challenge task, participants compete or collaborate to accomplish a common or shared task. The results of the challenge will be presented at the ASRU workshop event in the form of papers reporting the achievements of the participants, individually and/or as a whole. We invite organizers to concretely propose such challenge tasks in the form of a 1-2 page proposal. The proposal should include a description of
* The task and its intended goal
* The task organizers and key contact people for the various aspects of the task
* The data or shared resource that is to be used
* Details on the availability or its collection process
* Required labeling or other pre-processing and the expected timeline of this process
* Privacy concerns around the data or resource as it will be released to all participants
* Licensing terms or conditions for participants
* the evaluation process, how will a test set be defined, what figure of merit will be used to measure success, and how will a common scoring process be put in place to arrive at comparable results for all participants
* the timeline; when will training/test material be made available, when are participant (sub-)system submissions due
* the expected (number of) participants, and whether this is a new installment of an existing challenge or a new challenge series altogether
* any special requests or circumstances, e.g., required timing or format of the challenge execution
Participants will report their achievements in the form of regular format paper submissions to the ASRU workshop. These submissions will undergo the normal ASRU review process, but the organizers can suggest reviewers that would be particularly insightful for the challenge subject matter. Accepted papers will be organized in a special session at the conference (in poster format; the only format used at ASRU). The accepted papers will appear in the ASRU proceedings. Given the possibly lengthy process of organizing and executing a special challenge, prospective organizers are encouraged to submit proposals as soon as possible. The ASRU technical program committee will make acceptance decisions based on a rolling schedule -- i.e., proposals are reviewed as soon as they come in. Challenge proposals should be sent to Technical Program co-chair Michiel Bacchiani at michiel@google.com, and will be accepted until the end of 2014.
ELRA is very pleased to announce that the 10th edition of the Language Resources and Evaluation Conference will take place in Portorož (Slovenia) on May 23-28, 2016. More information will be available soon at:http://www.lrec-conf.org.
(2016-07-13) LabPhon 15: Speech Dynamics and Phonological Representation,Cornell University, Ithaca, NY USA
LabPhon 15:Speech Dynamics and Phonological Representation
July 13-16, 2016, Cornell University, Ithaca, NY USA
Phonological representations are dynamic, shaped by forces on diverse timescales. On the timescale of utterances, interactions between perceptual, motoric, and memory-related processes provide constraints on phonological representations. These same processes, embedded in learning systems and dynamic social networks, shape representations on developmental and life-span timescales, and in turn influence sound systems on historical timescales. Laboratory phonology, through its rich quantitative and experimental methodologies, contributes to our understanding of phonological systems by providing insight into the mechanisms from which representations emerge.
Conference themes:
Production dynamics:How are representations constructed and implemented in speech, and what does articulation reveal about the dynamics of production mechanisms? How do these mechanisms shape representations on longer timescales?
Perceptual dynamics:What forms of perceptual representation do speaker-hearers use and what are the temporal dynamics of perception? How does the interaction between perception and production constrain phonological systems on life-span and diachronic timescales?
Prosodic organization:What are the mechanisms of prosodic organization and how do they give rise to cross-linguistic differences? What are the connections between perception and production of prosodic structure?
Lexical dynamics and memory: How do experience and lexical memory influence phonological representations? What are the relations between lexical representation, production, and perception across diverse timescales?
Phonological acquisition and changes over the life-span:What is the nature of early representations and how do they change? How does learning a second-language interact with existing representations?
Social network dynamics:How does the structure of social networks influence phonological representations on diverse timescales? What are the roles of perception and production in relation to social network dynamics?
Contributions to any of these themes or to any other aspects of laboratory phonology will be welcome. A call for papers will be circulated in the fall of 2015.
