Nous avons le plaisir de vous informer que les inscriptions pour la 12ème édition de l'International Conference on Voice Physiology and Biomechanics (ICVPB2020), qui se tiendra du 18 au 20 Mars 2020 à Grenoble, sont ouvertes.

A cette occasion, nous célébrerons 40 ans de recherches scientifiques sur la physiologie de la voix humaine !

Vous trouverez ci-après les grandes thématiques qui seront abordées lors de la conférence:

• Physiologie et neurophysiologie du larynx et de la voix
• Contrôle neuromusculaire de la phonation saine et pathologique
• Acoustique, aérodynamique et cinématique de la production vocale
• Voix Chantée
• Bioacoustique : vocalisation animale
• Interactions fluide-structure-acoustique en phonation saine et pathologique
• Biomécanique des voies respiratoires supérieures : tissus mous, muscles, cartilages et os.
• Approches multi-échelles, micro et nanomécaniques
• Biologie moléculaire et cellulaire du pli vocal
• Mécanobiologie, cicatrisation, croissance et remodelage des tissus
• Médecine régénérative et ingénierie tissulaire
• Modélisation et simulation de la production vocale
• Analyse et synthèse de la voix
• Intelligence artificielle pour applications vocales
• Optique biomédicale, techniques d'imagerie pour l'évaluation de la voix
• Technologie portable

Deux jours de pré-cours (en anglais) se tiendront du 16 au 17 Mars (https://icvpb2020.sciencesconf.org/program). Pour l'inscription à ces pré-cours, un tarif préférentiel est proposé aux adhérents de l'AFCP et d'autres sociétés savantes françaises associées à cet événement scientifique : SFA, SFB, SFPL, AFPC-EVTA France.

Bien cordialement,

Lucie Bailly et Nathalie Henrich Bernardoni, pour le Comité d'Organisation ICVPB2020

icvpb2020@sciencesconf.org

Back

Top

The Lifelong learning Speaker Diarization Challenge 2020
https://lium.univ-lemans.fr/allies-evaluation/
*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*

CHALLENGE TASKs
______________________________________________________________________________________
The ALLIES evaluation focuses on  freeing speaker diarization
systems from the need of machine learning expert interventions upon two tasks:

        * Diarization Across time:
                automatic systems use the stream of incoming data
        to update their knowledge and adapt to new data in order
        to sustain performance across time

    * Lifelong learning speaker diarization
            systems are evaluated while processing a sequence
            of incoming audio documents with or without
            human-assisted learning including active learning (system initiative)
            or interactive learning (user initiative)
            Details are provided in the evaluation plan.

The ALLIES corpus consists of a new corpus of audio-visual
documents (news, debates, talk show.) including more
than 200 hours of TV shows from the French channel LCP.


BACKGROUND
______________________________________________________________________________________
Speech segmentation with speaker clustering, referred
to as speaker diarization, is a key pre-processing step
for several speech technologies including enriched automatic
speech recognition (ASR) or spoken document retrieval (SDR)
in very large multimedia repositories. The base accuracy of
such systems is of essential to allow applications to perform
adequately in real-world environments.
Performance of such systems usually degrades across time as
the distribution of incoming data moves away from the initial
training data (changes in accents, in recording conditions, etc).
Thus sustaining system performance across time requires frequent
interventions of machine learning experts which makes the maintenance
of such system very costly.


SCHEDULE
______________________________________________________________________________________
    From now until 31st of March: Registration for participants is open
    1st of March: Release of Development data
    1st of March: Beat platform is open for development
    1st of June: Evaluation data is released
    30th of June: Final submission
    End of July: Paper submission deadline
    November: Iberspeech conference in Valladolid


REGISTRATION
______________________________________________________________________________________
Send an email to :

        lifelong-speaker-evaluation@univ-lemans.fr

and specify
        * the task(s) you're willing to participate
        * the name of your team, that can be the name of your organization or any anonymous identity

More details on the evaluation plan.


EVALUATION PLAN
______________________________________________________________________________________
The evaluation plan and license agreement of the dataset can be downloaded here:

https://lium.univ-lemans.fr/allies-evaluation/


ORGANIZERS
Anthony Larcher, Le Mans Université, France
Olivier Galibert, LNE, France
Andre Anjos, IDIAP, Switzerland
Marta Ruiz Costa, UPC, Spain
Loïc Barrault, Sheffield University, UK

Back

Top

ESANN 2020: European Symposium on Artificial Neural Networks,

Computational Intelligence and Machine Learning

Bruges, Belgium, 22-23-24 April 2020

https://www.esann.org/.

The preliminary program of the ESANN 2020 conference is now available: https://www.esann.org/.

For 28 years the ESANN conference has become a major event in the field of neural computation and machine learning. ESANN is a selective conference focusing on fundamental aspects of artificial neural networks, machine learning, statistical information processing and computational intelligence. Mathematical foundations, algorithms and tools, and applications are covered.

ESANN 2020 will include the following sessions:

- Adversarial learning, robustness and fairness

- Image and signal processing, matrix computations and topological data

- Deep learning and graph neural networks

- Machine Learning Applied to Computer Networks

- Quantum Machine Learning

- Recurrent networks and reinforcement learning

- Unsupervised learning

- Feature selection and dimensionality reduction

- Statistical learning and optimization

- Tensor Decompositions in Deep Learning

- Image and text analysis

- Learning from partially labeled data

- Machine learning in the pharmaceutical industry

- Frontiers in Reservoir Computing

- Language processing in the era of deep learning

- Supervised learning

The program of the conference can be found at https://www.esann.org/, together with practical information about the conference venue, registration, etc.

The conference will be held in Bruges (also called 'Venice of the North'), one of the most beautiful medieval towns in Europe. Bruges can be reached by train from Brussels in less than one hour (frequent trains). Designated as the 'Venice of the North', the city has preserved all the charms of the medieval heritage. Its centre, which is inscribed on the Unesco World Heritage list, is in itself a real open air museum.

 ========================================================

ESANN - European Symposium on Artificial Neural Networks,

Computational Intelligence and Machine Learning

https://www.esann.org/

* For submissions of papers, reviews, registrations:

Michel Verleysen

Univ. cath. de Louvain - Machine Learning Group

3, pl. du Levant (L5.03.02) - B-1348 Louvain-la-Neuve - Belgium

tel: +32 10 47 25 51 - fax: + 32 10 47 25 98

mailto:esann@uclouvain.be

* Conference secretariat

d-side conference services

24 av. L. Mommaerts - B-1140 Evere - Belgium

tel: + 32 2 730 06 11 - fax: + 32 2 730 06 00

mailto:esann@uclouvain.be

Back

Top

 ----------------------------------------------
                       Announcement
    6th CHiME Speech Separation and Recognition Challenge
                  Launch Date: December 2019
               Workshop: Barcelona, May 4, 2020

       htttp://spandh.dcs.shef.ac.uk/chime_challenge
       ----------------------------------------------

Dear colleague,

It gives us great pleasure to announce the 6th CHiME Speech Separation
and Recognition Challenge (CHiME-6).

The new challenge will revisit the CHiME-5 24-microphone dinner party
conversational speech recognition scenario by:
- providing an accurate array synchronization script,
- introducing a new multichannel diarization track in the line of the
DIHARD-II challenge
- offering upgraded, state-of-the-art diarization, enhancement, and
recognition baselines.

FORUM

If you are considering participating, please join the CHiME Google
group for discussions and further announcements.
https://groups.google.com/forum/#!forum/chime5/join

DATASET LICENCE

Participants will need to acquire a licence for the CHiME-5 dataset.
Licence applications are typically processed within 48 hours. Apply
now at:
https://licensing.sheffield.ac.uk/i/data/chime5.html
Non-commercial license requests are processed within 2-3 days once
they have been approved by an authorized representative of your
institution. Commercial licenses are also available for companies and
are required for challenge participation. Note that licenses acquired
before Dec 31, 2018, are no longer valid.

IMPORTANT DATES

Dec, 2019 ? Release of data and baseline systems
10th April, 2020 ? System submission
4th May, 2020 ? CHiME-6 Workshop (satellite of ICASSP 2020) and
release of results

ORGANISERS

Shinji Watanabe, Johns Hopkins University, USA
Michael Mandel, CUNY, USA
Jon Barker, University of Sheffield, UK
Emmanuel Vincent, Inria, France

Back

Top

Now Accepting Papers for ICASSP 2020

The 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing heads to Barcelona, Spain in May, and the conference paper submission site is now live!

Back

Top

Call for Paper:  Industry Track @ LREC 2020

LREC Industry Track will take place within LREC 2020 in Marseille, France, May 11-16, 2020
 
The European Language Resource Association (ELRA, www.elra.info) is glad to announce the 12th edition of LREC, organized with the support of international associations and a number of industrial partners and supporters.

Since the first LREC held in Granada in 1998, LREC has become the major event on Language Resources (LRs) and Evaluation for Language Technologies (LT) with over 1200 attendees from all over the world. LREC provides a unique forum for researchers, industrials and funding agencies from across a wide spectrum of areas to discuss problems and opportunities, find new synergies and promote initiatives for international cooperation, in support to investigations in language sciences, progress and innovation in language technologies and development of corresponding products, services and applications, and standards.

For the second time and as a hot LREC 2020 topic, an industry track will take place during the main conference (May 13-15, 2020).

 
Track Description

Human language technologies have become increasingly important parts of our lives. These technologies have emerged from decades of collaborations between academic and industrial research organizations often with financial and research support from the public sector; collaborations are made possible by the unique strengths of both communities and a set of shared practices (algorithms, evaluation methods, datasets, and the like). But despite this, there are substantial differences between research in academic and industrial settings.
In contrast to academic research: industrial speech and language technologies may pose unique challenges of scale; language resources from industry may demand different algorithms or evaluation methodologies than in academic settings; and the practices of academic and industrial settings may converge on distinct methods for the same problem; industrial systems and practices may pose ethical challenges not necessarily present in academic settings.

 
Topics of Interest

Topics include but not limited to:

1. Industrial systems
For this topic, we welcome submissions which discuss industrial systems. They may describe technical innovations which are enabled by the industrial setting, or they may describe the implementation of a deployed industrial system. We also welcome submissions which discuss failures to replicate 'state-of-the-art' performance when provided with the affordances of an industrial setting. Finally, we also welcome opinion papers which discuss similarities and differences between academic and industrial practices for system development and evaluation, or which consider ethical issues specific to systems deployed at industry scale.

2. Tools and platforms for data collection
Data collected in an industry setting may pose specific technical, legal, and ethical challenges not normally encountered in academic settings. The infrastructure within which developers in industry operate can provide tremendous advantages, but also unique challenges. There can be significant differences in the context of a tool's operator or a data platform's customer in industry vs. academic applications. Platforms may be globally distributed, and the scale itself of the data and of the deployment of industry technologies can add significant complexity, which may demand innovative approaches. Industry developers may also face special problems in defining users, their orientation to their tasks, and what constitutes a successful interaction from the standpoint of the user and of data acquisition efforts. We welcome submissions which discuss industrial tools and platforms used to collect data.

3. Human computation in industry
Industrial language technologies depend on machine learning methods, which in turn require large, diverse collections of labeled data collected from humans for rapid iterative development and refinement. We welcome submissions which discuss issues in experimental design for human computation, the challenges of quality, diversity, and representation in crowdsourcing, and ethical issues posed by data collection via crowdsourcing and outsourcing.

4. Less-resourced languages
One goal for this year's LREC is to strengthen connections with the Mediterranean speech and language communities, in particular for the less resourced languages. These cover a large number of languages, with associated varieties (European languages, varieties of Semitic languages, indigenous languages, spoken-only languages, etc.). Therefore we welcome submissions which discuss industrial resources and technologies specific to the challenges posed by such languages.

5. Spoken languages and dialects
We are particularly interested in work which describes industrial resources and technologies for spoken languages, non-standard dialects, and therefore we welcome submissions which focus on these topics, especially those submissions which contrast spoken and written language?or standard and non-standard
language?resources and technologies.
 
Submission

We encourage submissions of papers for oral or poster presentation. Papers should follow the LREC stylesheet. The working language of the track is English. Submitted papers must be written and delivered in English and be up to 4 pages in length.

Submission page: https://www.softconf.com/lrec2020/IndustryTrack/.


Identify, Describe and Share your LRs!

Describing your language resources (LRs) in the LRE Map is now a normal practice in the submission procedure of LREC (introduced in 2010 and adopted by other conferences). This LREC feature is available to submissions within this track and highly recommended. To continue the efforts initiated at LREC 2014 about ?Sharing LRs? (data, tools, web-services, etc.), authors will have the possibility, when submitting a paper, to upload LRs in a special LREC repository. This effort of sharing LRs, linked to the LRE Map for their description, may become a new ?regular? feature for conferences in our field, thus contributing to creating a common repository where everyone can deposit and share data.

As scientific work requires accurate citations of referenced work so as to allow the community to understand the whole context and also replicate the experiments conducted by other researchers, LREC 2020 endorses the need to uniquely Identify LRs through the use of the International Standard Language Resource Number (ISLRN, www.islrn.org ), a Persistent Unique Identifier to be assigned to each LR. The assignment of ISLRNs to LRs cited in LREC papers will be offered at submission time.

 
Important Dates/Deadlines

? Paper submission: 28 February 2020
? Notification of acceptance: 13 March 2020
? Camera-ready paper: 03 April 2020
? Track Date: to be defined (13-15 May 2020)


Organizing Committee
? tbd

Contact: Khalid Choukri at choukri@elda.org

Back

Top

DEADLINE EXTENSION

March 13, 2020 (23:59 GMT+1) is the new deadline for submitting your final paper(s) to the Main conference.


Submit your LREC paper(s) by March 13, 2020:  https://www.softconf.com/lrec2020/main/

Register online: https://lrec2020.lrec-conf.org/en/lrec2020-registration/

March 19, 2020 (17:00 GMT+1) is the new deadline for registering to LREC 2020 at early-bird rate

Book a hotel room for the conference & tours: https://lrec2020.lrec-conf.org/en/conference-venue/accommodation-lrec2020/

Contact us: lrec@lrec-conf.org (general matters) 

- registration@lrec-conf.org (registration)
 www.lrec-conf.org/lrec2020
Follow us on Twitter: @LREC2020

*********************************************************

LREC 2020, 12th Conference on Language Resources and Evaluation -
Palais du Pharo, Marseille, France
11-16 May 2020

Main Conference: 13-14-15 May 2020
Workshops and Tutorials: 11-12 & 16 May 2020

Conference web site: https://lrec2020.lrec-conf.org/
Twitter: @LREC2020


FIRST CALL FOR PAPERS

The European Language Resources Association (ELRA) is glad to announce the 12th edition of LREC, organised with the support of national and international organisations among which AFCP, AILC, ATALA, CLARIN, ILCB, LDC, ...

CONFERENCE AIMS
LREC is the major event on Language Resources (LRs) and Evaluation for Human Language Technologies (HLT). LREC aims to provide an overview of the state-of-the-art, explore new R&D directions and emerging trends, exchange information regarding LRs and their applications, evaluation methodologies and tools, on-going and planned activities, industrial uses and needs, requirements coming from e-science and e-society, with respect both to policy issues as well as to scientific/technological and organisational ones.

LREC provides a unique forum for researchers, industrials and funding agencies from across a wide spectrum of areas to discuss issues and opportunities, find new synergies and promote initiatives for international cooperation, in support of investigations in language sciences, progress in language technologies (LT) and development of corresponding products, services and applications, and standards.

CONFERENCE TOPICS

Issues in the design, construction and use of LRs: text, speech, sign, gesture, image, in single or multimodal/multimedia data

•     Guidelines, standards, best practices and models for LRs interoperability
•     Methodologies and tools for LRs construction and annotation
•     Methodologies and tools for extraction and acquisition of knowledge
•     Ontologies, terminology and knowledge representation
•     LRs and Semantic Web (including Linked Data, Knowledge Graphs, etc.)
•     LRs and Crowdsourcing
•     Metadata for LRs and semantic/content mark-up

Exploitation of LRs in systems and applications

•     Sign language, multimedia information and multimodal communication
•     LRs in systems and applications such as: information extraction, information retrieval, audio-visual and multimedia search, speech dictation, meeting transcription, Computer Aided Language Learning, training and education, mobile communication, machine translation, speech translation, summarisation, semantic search, text mining, inferencing, reasoning, sentiment analysis/opinion mining, etc.
•     Interfaces: (speech-based) dialogue systems, natural language and multimodal/multisensory interactions, voice-activated services, etc.
•     Use of (multilingual) LRs in various fields of application like e-government, e-participation, e-culture, e-health, mobile applications, digital humanities, social sciences, etc.
•     Industrial LRs requirements
•     User needs, LT for accessibility

LRs in the age of deep neural networks

•     Semi-supervised, weakly-supervised and unsupervised machine learning approaches
•     Representation Learning for language
•     Techniques for (semi-)automatically generating training data
•     Cross-language NLP & Cross-domain NLP with reduction of human effort

Issues in LT evaluation

•     LT evaluation methodologies, protocols and measures
•     Validation and quality assurance of LRs
•     Benchmarking of systems and products
•     Usability evaluation of HLT-based user interfaces and dialogue systems
•     User satisfaction evaluation

General issues regarding LRs & Evaluation

•     International and national activities, projects and initiatives
•     Priorities, perspectives, strategies in national and international policies for LRs
•     Multilingual issues, language coverage and diversity, less-resourced languages
•     Open, linked and shared data and tools, open and collaborative architectures
•     Replicability and reproducibility issues
•     Organisational, economical, ethical and legal issues

LREC 2020 HOT TOPICS

Less Resourced and Endangered Languages
Special attention will be devoted to less resourced and endangered languages: it is expected that LREC2020 makes room to activities carried out to support indigenous languages, building on the United Nations/UNESCO International Year of Indigenous Languages being celebrated in 2019.

Language and the Brain
Studying the neural basis of language helps in understanding both language processing and the brain mechanisms. LREC2020 will encourage all submissions addressing language and the brain. Among possible subtopics, submissions could focus on new datasets and resources (neuroimaging, controlled corpora, lexicons, etc.), methods aiming at new multimodal experimentations (e.g. EEG in virtual reality), language processing applications (e.g. brain decoding, brain-computer interfaces), etc.

Machine/Deep Learning
The availability of LRs is a key element of the development of high quality Human Language Technologies based on AI/Machine Learning approaches, and LREC is the best place to get access to this data, in many languages and for many domains. In addition to submissions addressing ML issues based on large quantities of data, those applied to languages for which only small, noisy or sparse data exist are also most welcomed.

DESCRIBE AND SHARE YOUR LRs!
In addition to describing your LRs in the LRE Map ? now a normal step in the submission procedure of many conferences ? LREC recognises the importance of sharing resources and making them available to the community.
When submitting a paper, you will be offered the possibility to share your LRs (data, tools, web-services, etc.), uploading them in a special LREC repository set up by ELRA. Your LRs will be made available to all LREC participants before the conference, to be re-used, compared, analysed. This effort of sharing LRs, linked to the LRE Map for their description, contributes to creating a common repository where everyone can deposit and share data.

PROGRAMME
The Scientific Programme will include invited talks, oral presentations, poster and demo presentations, and panels, in addition to a keynote address by the winner of the Antonio Zampolli Prize.
We will also organise an Industrial Track and a Reproducibility Track: for these there will be separate Calls.

SUBMISSIONS AND DATES

Submission of oral and poster (or poster+demo) papers: 25 November 2019

    LREC2020 asks for full papers from 4 pages to 8 pages (plus more pages for references if needed) , which must strictly follow the LREC stylesheet which will be available on the conference website. Papers must be submitted through the LREC2020 submission platform (it uses START from Softconf) and will be peer-reviewed.

Submission of proposals for workshops, tutorials and panels: 24 October 2019

    Proposals should be submitted via an online form on the LREC website and will be reviewed by the Programme Committee.

PROCEEDINGS

The Proceedings will include both oral and poster papers, in the same format.

There is no difference in quality between oral and poster presentations. Only the appropriateness of the type of communication (more or less interactive) to the content of the paper will be considered.

LREC 2010, LREC 2012 and LREC 2014 Proceedings are included in the Thomson Reuters Conference Proceedings Citation Index. The other editions are being processed.

LREC Proceedings are indexed in Scopus (Elsevier).

Substantially extended versions of papers selected by reviewers as the most appropriate will be considered for publication in a special issue of the Language Resources and Evaluation Journal published by Springer (a SCI-indexed journal).

CONFERENCE PROGRAMME COMMITTEE
Nicoletta Calzolari ? CNR, Istituto di Linguistica Computazionale ?Antonio Zampolli?, Pisa - Italy (Conference chair)
Frédéric Béchet ? LIS-CNRS, Aix-Marseille University, Marseille- France
Philippe Blache ? CNRS & Aix-Marseille University, Marseille- France
Christopher Cieri ? Linguistic Data Consortium, Philadelphia - USA
Khalid Choukri ? ELRA, Paris - France
Thierry Declerck ? DFKI GmbH, Saarbrücken - Germany
Hitoshi Isahara ? Toyohashi University of Technology, Toyohashi - Japan
Bente Maegaard ? Centre for Language Technology, University of Copenhagen, Copenhagen - Denmark
Joseph Mariani ? LIMSI-CNRS, Orsay - France
Asuncion Moreno ? Universitat Politècnica de Catalunya, Barcelona - Spain
Jan Odijk ? UIL-OTS, Utrecht - The Netherlands
Stelios Piperidis ? Athena Research Center/ILSP, Athens - Greece

CONFERENCE EDITORIAL COMMITTEE
Sara Goggi ? CNR, Istituto di Linguistica Computazionale ?Antonio Zampolli?, Pisa - Italy
Hélène Mazo ? ELDA/ELRA, Paris - France

Back

Top

FIRST CALL FOR PAPERS


REPROLANG 2020
Shared Task on the Reproduction of Research Results in Science and Technology of Language
(part of LREC 2020 conference)
Marseille, France
May 13-15, 2020
http://wordpress.let.vupr.nl/lrec-reproduction


We are very pleased to announce REPROLANG 2020, the Shared Task on the Reproduction of
Research Results in Science and Technology of Language, organized by ELRA - European
Language Resources Association with the technical support of CLARIN - European Research
Infrastructure for Language Resources and Technology, as part of the LREC 2020 conference.

BACKGROUND

Scientific knowledge is grounded on falsifiable predictions and thus its credibility and
raison d?être relies on the possibility of repeating experiments and getting similar
results as originally
obtained and reported. In many young scientific areas, including ours, acknowledgement
and promotion of the reproduction of research results need very much to be increased.

For this reason, a special track on reproducibility is included into the LREC 2020
conference regular program (side by side with other sessions on other topics) for papers
on reproduction of research results, and the present specific community-wide shared task
is launched to elicit and motivate the spread of scientific work on reproduction. This
initiative builds on the previous pioneer LREC workshops on reproducibility 4REAL 2016
and 4REAL 2018.


SHARED TASK

The shared task is of a new type: it is partly similar to the usual competitive shared
tasks --- in the sense that all participants share a common goal; but it is partly
different to previous shared tasks --- in the sense that its primary focus is on seeking
support and confirmation of previous results, rather than on overcoming those previous
results with superior ones. Thus instead of a competitive shared task, with each
participant struggling for an individual top system that scores as far as possible from a
rough baseline, this will be a cooperative shared task, with participants struggling for
systems that reproduce as close as possible an original complex research experiment and
thus eventually reinforcing the level of reliability on its results by means of their
eventually convergent outcomes. Concomitantly, like with competitive shared tasks, in the
process of participating in the collaborative shared task, new ideas for improvement and
new advances beyond the reproduced results find here an excellent ground to be ignited.

We invite researchers to reproduce the results of a selected set of articles, which have
been offered by the respective authors with their consent to be used for this shared
task. Papers submitted for this task are expected to report on reproduction findings, to
document how the results of the original paper were reproduced, to discuss
reproducibility challenges, to inform on time, space or data requirements found
concerning training and testing, to ponder on lessons learned, to elaborate on
recommendations for best practices, etc.
Submissions that in addition to the reproduction exercise, report also on results of the
replication of the selected tasks with other languages, domains, data sets, models,
methods, algorithms, downstream tasks, etc. are also encouraged. These should permit to
gain insight also into the robustness of the replicated approaches, their learning curves
and potential of incremental performance, their capacity of generalization, their
transferability across experimental circumstances and into eventual real-life usage
scenarios, their suitability to support further progress, etc.


PUBLICATION

LREC conferences have one of the top h5-index scores of research impact among the world
class venues for research on Human Language Technology.

Accepted papers for the shared task will be published in the Proceedings of the LREC 2020
main conference. LREC Proceedings are freely available from ELRA and ACL Anthology. They
are indexed in Scopus (Elsevier) and in DBLP. LREC 2010, LREC 2012 and LREC 2014
Proceedings are included in the Thomson Reuters Conference Proceedings Citation Index
(the other editions are being processed).

Substantially extended versions of papers selected by reviewers as the most appropriate
will be considered for publication in special issues of the Language Resources and
Evaluation Journal published by Springer (a SCI-indexed journal).


IMPORTANT DATES

November 25, 2019: deadline for paper submission (aligned with LREC 2020)
November 27: deadline for projects in gitlab.com to go public
February 14, 2020: notification of acceptance
May 11-16: LREC conference takes place


SELECTED TASKS

The Selection Committee has selected a broad range of papers and tasks.

Chapter A: Lexical processing

Task A.1: Cross-lingual word embeddings

Artetxe, Mikel, Gorka Labaka, and Eneko Agirre. 2018. ?A robust self-learning method for
fully unsupervised cross-lingual mappings of word embeddings?. In Proceedings of the 56th
Annual Meeting of the Association for Computational Linguistics (ACL 2018), pp. 789?798.
http://aclweb.org/anthology/P18-1073
Major reproduction comparables: Accuracy scores (tables 1 to 4).

Task A.2: Named entity embeddings

Newman-Griffis, Denis, Albert M Lai, and Eric Fosler-Lussier. 2018. ?Jointly Embedding
Entities and Text with Distant Supervision?. In Proceedings of The Third Workshop on
Representation Learning for NLP, pp. 195?206.
http://aclweb.org/anthology/W18-3026
Major reproduction comparables: Spearman?s ? scores for semantic similarity predictions
(tables 3 and 4), and accuracy scores (table 6).

Chapter B: Sentence processing

Task B.1: POS tagging

Bohnet, Bernd, Ryan McDonald, Gonçalo Simões, Daniel Andor, Emily Pitler, and Joshua
Maynez. 2018. ?Morphosyntactic Tagging with a Meta-BiLSTM Model over Context Sensitive
Token Encodings?. In Proceedings of the 56th Annual Meeting of the Association for
Computational Linguistics (ACL 2018), pp. 2642?2652.
http://aclweb.org/anthology/P18-1246
Major reproduction comparables: f-score values (tables 2 to 8).

Task B.2: Sentence semantic relatedness

Gupta, Amulya, and Zhu Zhang. 2018. ?To Attend or not to Attend: A Case Study on
Syntactic Structures for Semantic Relatedness?. In Proceedings of the 56th Annual Meeting
of the Association for Computational Linguistics (ACL 2018), pp. 2116?2125.
http://aclweb.org/anthology/P18-1197
Major reproduction comparables: Pearson?s r and Spearman?s ? scores for the semantic
relatedness
(table 1), and f-score values for paraphrase detection (table 2).

Chapter C: Text processing

Task C.1: Relation extraction and classification

Rotsztejn, Jonathan, Nora Hollenstein, and Ce Zhang. 2018. ?ETH-DS3Lab at SemEval-2018
Task 7: Effectively Combining Recurrent and Convolutional Neural Networks for Relation
Classification and Extraction?. In Proceedings of the 12th International Workshop on
Semantic Evaluation (SemEval 2018), pp. 689?696.
http://aclweb.org/anthology/S18-1112
Major reproduction comparables: precision, recall and f-score values (tables 3 and 4).

Task C.2: Privacy preserving representation

Li, Yitong, Timothy Baldwin, and Trevor Cohn. 2018. ?Towards Robust and
Privacy-preserving Text Representations?. In Proceedings of the 56th Annual Meeting of
the Association for Computational Linguistics (ACL 2018), pp. 25-30.
http://aclweb.org/anthology/P18-2005
Major reproduction comparables: POS accuracy scores (tables 1 and 2), and sentiment
analysis
f-score scores (table 3).

Task C.3: Language modelling

Howard, Jeremy, and Sebastian Ruder. 2018. ?Universal Language Model Fine-tuning for Text
Classification?. In Proceedings of the 56th Annual Meeting of the Association for
Computational Linguistics (ACL 2018), pp. 328?339.
http://aclweb.org/anthology/P18-1031
Major reproduction comparables: Error rate (%) scores in sentiment analysis and question
classification tasks (tables 2 and 3).

Chapter D: Applications

Task D.1: Text simplification

Nisioi, Sergiu, Sanja Stajner, Simone Paolo Ponzetto, and Liviu P. Dinu. 2017.
?Exploring Neural Text Simplification Models?. In Proceedings of the 55th Annual Meeting
of the Association for Computational Linguistics (ACL 2017), pp. 85-91.
http://aclweb.org/anthology/P/P17/P17-2014.pdf
Major reproduction comparables: Averaged human evaluation scores, by 3 evaluators,
in 1 to 5 and -2 to +2 scales (table 2).

Task D.2: Language proficiency scoring

Vajjala, Sowmya, and Taraka Rama. 2018. ?Experiments with Universal CEFR classifications?.
In Proceedings of Thirteenth Workshop on Innovative Use of NLP for Building Educational
Applications, pp. 147?153.
http://aclweb.org/anthology/W18-0515
Major reproduction comparables: f-score values (tables 2, 3 and 4).

Task D.3: Neural machine translation

Vanmassenhove, Eva, and Andy Way. 2018. ?SuperNMT: Neural Machine Translation with
Semantic Supersenses and Syntactic Supertags?. In Proceedings of the 56th Annual Meeting
of the Association for Computational Linguistics (ACL 2018), pp. 67?73.
http://aclweb.org/anthology/P18-3010
Major reproduction comparables: BLEU scores (tables 1 and 2; plots in figures 2, 3 and 4).

Chapter E: Language resources

Task E.1: Parallel corpus construction

Brunato, Dominique, Andrea Cimino, Felice Dell'Orletta, and Giulia Venturi. 2016.
?PaCCSS-IT: A Parallel Corpus of Complex-Simple Sentences for Automatic Text
Simplification?. In Proceedings of the 2016 Conference on Empirical Methods in Natural
Language Processing (EMNLP 2016), pp. 351-361.
https://aclweb.org/anthology/D16-1034
Major reproduction comparables: data set.

Participants are expected to obtain the data and tools for the reproduction from the
information provided in the paper. Using the description of the experiment is part of the
reproduction exercise.
SUBMISSION
The START platform of LREC 2020 will be used for the submission of the following required
elements: A paper describing the reproduction effort, and a link to the software and data
used to obtain the results reported in the paper (more details below). The submitted
materials and results will be checked by a CLARIN panel. Papers will be peer-reviewed.


PAPER PREPARATION
REPROLANG 2020 invites the submission of full papers from 4 pages to 8 pages (plus more
pages for references if needed). These submissions must strictly follow the LREC 2020
conference stylesheet which will be available on the conference website.


MATERIALS PREPARATION
To be checked by a CLARIN panel and the submission to be complete, the software used to
obtain the results reported in the paper must be made available as a docker container
through a project in gitlab. Detailed instructions are available at
https://gitlab.com/CLARIN-ERIC/reprolang/ For technical support, the CLARIN team can be
contacted at reprolang-tc@clarin.eu or an issue can be created under
https://gitlab.com/CLARIN-ERIC/reprolang/issues.

Submissions are done via the START conference management system used by LREC 2020 and
include the following elements:
- url address of your gitlab.com project
- url of the tar.gz with the datasets - the md5 checksum of the above tar.gz
- .pdf with the paper, which must include the above url of your gitlab.com project, and
the above commit hash and tag

The project in gitlab.com should be made public within 2 days after the submission
deadline.

PRESENTATION Papers accepted for publication will be presented in a specific session of
the LREC main conference. There is no difference in quality between oral and poster
presentations. Only the appropriateness of the type of communication (more or less
interactive) to the content of the paper will be considered. The format of the
presentations will be decided by the Program Committee. The proceedings will include both
oral and poster papers in the same format.

REGISTRATION
For a selected paper to be included in the programme and to be published in the
proceedings, at least one of its authors must register for the LREC 2020 conference by
the early bird registration deadline. A single registration only covers one paper,
following the general LREC policy on registration. Registration service is to be found at
the LREC 2020 website.


CONTACTS
About the shared task:
Piek Vossen
p.t.j.m.vossen@vu.nl

About the preparation and submission of materials:
reprolang-tc@clarin.eu
REPROLANG 2020 website: http://wordpress.let.vupr.nl/lrec-reproduction


ORGANIZATION

Steering Committee

António Branco, University of Lisbon (chair of Steering Committee)
Nicoletta Calzolari, ILC, Pisa (co-chair of Steering Committee)
Gertjan van Noord, University of Groningen (chair of Task Selection Committee)
Piek Vossen, VU University Amsterdam (chair of Program Committee)


Task Selection Committee

Gertjan van Noord, University of Groningen (chair)
Tim Baldwin, University of Melbourne
António Branco, University of Lisbon
Nicoletta Calzolari, ILC, Pisa
Ça?r? Çöltekin, University of Tuebingen
Nancy Ide, Vassar College, New York
Malvina Nissim, University of Groningen
Stephan Oepen, University of Oslo
Barbara Plank, University of Copenhagen
Piek Vossen, VU University Amsterdam
Dan Zeman, Prague University

Program Committee

several invitations awaiting an answer marked with [!]

Piek Vossen, VU University Amsterdam (chair)
  [!]Gilles Adda, LIMSI-CNRS, Paris
  [!]Eneko Agirre Basque University
Francis Bond, NanyangTechnical University, Singapore
António Branco, University of Lisbon

Nicoletta Calzolari, ILC, Pisa
Kevin Cohen, University of Colorado Boulder
 [!]Thierry Declerck declerck@dfki.de, DFKI Saarbruecken
  [!]John McCrae, Galway University
Nancy Ide , Vassar College, New York
  [!]Antske Fokkens VU University Amsterdam
Karën Fort, University of Paris-Sorbonne
  [!] Cyril Grouin, LIMSI-CNRS, Paris
Mark Liberman, University of Pennsylvania
  [!] Margo Mieskis
  [!] Aurélie Névéol, LIMSI-CNRS, Paris
Gertjan van Noord, University of Groningen
Stephan Oepen, University of Oslo
  [!]Ted Pedersen, University of Minnesota
Senja Pollak, Jozef Stefan Institute, Ljubljana
  [!]Paul Rayson, Lancaster University
Martijn Wieling, University of Groningen



Technical Committee
reprolang-tc@clarin.eu
Dieter Van Uytvanck, CLARIN (chair)
André Moreira, CLARIN
Twan Goosen, CLARIN
João Ricardo Silva, CLARIN and University of Lisbon
Luís Gomes, CLARIN and University of Lisbon
Willem Elbers, CLARIN

Back

Top

LREC Workshop on Cross-Language Search and Summarization of Text and Speech

May 16, 2020

Palais du Pharo, Marseilles, France



Call for Papers (http://users.umiacs.umd.edu/~oard/clssts)

 

In today?s global world, people may need  Cross-Language Information Retrieval (CLIR) enables end users to issue queries in their own language, but provides results from multiple languages around the world, often using translation so that the end user can quickly understand whether the retrieved results are relevant. Cross-language summarization can make it easier for an end user to determine if a document is relevant by providing a summary in the user?s language of the foreign language document, highlighting the evidence for relevance.  When the foreign language is a low-resource language, cross-language search and summarization are more difficult; translation capabilities may be poor and the lack of resources makes it difficult to train CLIR and summarization systems.  To complicate matters even more, when the collection contains speech as well as text, producing accurate search results and generating comprehensible summaries is even more difficult.

 

This workshop aims to stimulate the collection and provision of resources that can improve systems that perform cross-language search and summarization.  To facilitate dissemination of information about existing resources, the workshop will feature keynote speeches and panels by people who have worked in this area, have cross-language resources to share, or can describe ongoing research programs and shared tasks. Papers are also solicited that describe recent and current research in these areas, that describe relevant resources, or that stake out positions on the directions in which the authors think the field should move.

 

To set the stage, the organizers will provide two small spoken language test collections that include waveforms, transcriptions and possibly queries with relevance judgments. These are conversational genres, one in Somali (a very-low resource language) and the other in Bulgarian (a moderate-resource language) both of which include approximately 80 hours of speech. We will welcome papers that provide results on these test collections as well as results on any datasets that are available from by ELDA, LDC, or other repositories. Participants are also encouraged to describe other datasets that they have access to and to report results on these.

 

We solicit papers on research that broadly relates to supporting information access to lower-resource languages addressing topics such as the following:

 

Test collections for evaluating CLIR

Development of new cross-lingual resources

Datasets for cross-lingual summarization

Methods for CLIR

CLIR over speech

Evidence generation for CLIR

Methods for cross-lingual summarization

Methods for cross-lingual query-focused summarization

Snippet generation

Speech summarization

Multilingual language generation

Zero-shot learning and domain adaptation

Explainable methods for cross-lingual NLP

 

 

Paper length: Both long papers (8 pages plus references) and short papers (4 pages plus references) are welcome. Papers must  follow the LREC stylesheet available here. Papers must be submitted through START at this link: https://www.softconf.com/lrec2020/CLSSTS2020/

 

 

Important dates:

 Submissions due: February 15th, 11:59pm AOE

Acceptance notifications: March 12th

Camera ready copy due: April 1st

Workshop date: May 16th



Contact person: Kathy McKeown, Kathy@cs.columbia.edu

 

Organizing Committee:

James Allan, UMass Amherst (USA)

Lu Wang, Northeastern University (USA)

Kathy McKeown, Columbia University (USA)

Douglas W. Oard, University of Maryland (USA)

Steve Renals, University of Edinburgh (UK)

Richard Schwartz, BBN (USA)

 

Identify, describe and share your Lexical Resource (LR):

Authors will have the opportunity, when submitting a paper, to upload LRs in a special LREC repository.  This effort of sharing LRs, linked to the LRE Map for their description contributes to creating a common repository where everyone can deposit and share data. As scientific work requires accurate citations of referenced work so as to allow the community to understand the whole context and also replicate the experiments conducted by other researchers, LREC 2020 endorses the need to uniquely Identify LRs through the use of the International Standard Language Resource Number (ISLRN, www.islrn.org), a Persistent Unique Identifier to be assigned to each Language Resource. The assignment of ISLRNs to LRs cited in LREC papers  will be offered at submission time.



--
The University of Edinburgh

Back

Top

Associated with Speech Prosody 2020 in Tokyo there will be:

Workshops,  all May 23rd:

- Prosodic Variation: the role of past and present contact in multilingual societies, abstracts due Jan 31

- Word Order and Prosody, papers due Dec 20

- Representations in Intonational Phonology: How different is Intonational Phonology, and from what?, papers due Dec 20

Special Sessions:

- Temporal Articulation as it relates to communicative prosody, papers due Dec 20

- Acquisition of Interactive Emotional/Social Affective Prosody, papers due Dec 20

- The Third Prosody Visualization Challenge, How well does your system visualize communicative and/or interactive prosody?, submissions due April 25

Tutorials, all May 24th:

- Streamlining the Processing of F0 data using the R package ‘intonation’

- Prosodic Analysis of Speech Corpora Using Praaline and R

- Guide to Annotation with PoLaR

Details for all are at https://sp2020.jpn.org/events/

And, as a reminder, papers for the Speech Prosody conference itself

are also due December 20th.

I'm also pleased to announce that the proceedings of Speech

Prosody 2014 are now, at last, available in the ISCA Archive,

https://www.isca-speech.org/iscaweb/index.php/online-archive , thanks

to the hard work of Rachida Ganga, Aoju Chen, and Martin Cooke.

Nigel Ward,  ISCA Speech Prosody Special Interest Group Chair

Professor of Computer Science, University of Texas at El Paso

CCSB 3.0408,  +1-915-747-6827

nigel@utep.edu    http://www.cs.utep.edu/nigel/   

Back

Top

*2ième Appel Démos JEP-TALN'20  (JEP-TALN-RECITAL 2020)*
Conférence JEP 2020 | TALN 2020 | RÉCITAL 2020
8 au 12 juin 2020
Nancy, France
https://jep-taln2020.loria.fr/

La sixième édition conjointe de la conférence JEP-TALN-RECITAL sera organisée à Nancy du
8 au 12 juin 2020 (https://jep-taln2020.loria.fr/) .

La conférence inclut des démonstrations dans la cadre du TAL et du traitement automatique
de la parole, ou de son étude. Ce présent message est un appel à démonstration, et ne
doit pas être confondu avec les appels à communications indépendants pour les trois
conférences JEP, TALN et RECITAL.


*Thématiques des démonstrations*

Nous sollicitons des communications pouvant porter sur tous les thèmes habituels du TAL
et du traitement automatique de la parole, ou de son étude. Plus précisément, nous
reprenons les intitulés des thèmes listés dans les appels à soumissions,
en TAL :
- Phonétique, phonologie, morphologie, étiquetage morphosyntaxique,
- Syntaxe, grammaires, analyse syntaxique, chunking,
- Sémantique, pragmatique, discours,
- Sémantique lexicale et distributionnelle,
- Aspects linguistiques et psycholinguistiques du TAL,
- Ressources pour le TAL ou la parole,
- Méthodes d?évaluation pour le TAL,
- Applications du TAL (recherche et extraction d?information, question-réponse,
traduction,génération, résumé, dialogue, analyse d?opinions, etc.),
- TAL et multi-modalité (parole, vision, etc.),
- TAL et multilinguisme,
- TAL pour le Web et les réseaux sociaux,
- TAL et langues peu dotées,
- TAL et langue des signes,
- implications sociales et éthiques du TAL,
- TAL et linguistique de corpus,
- TAL et Humanités numériques.
et en parole :
- traitement automatique de la parole,
- reconnaissance, synthèse, traduction, dialogue,
- compréhension, codage,
- acquisition et apprentissage,
- production, perception et cognition,
- santé, troubles et handicap,
- phonétique, phonologie, prosodie,
- géolinguistique et sociolinguistique,
- ressources et évaluation.


*Types de communication - Démonstrations*

Les organisateurs de ces conférences ont le plaisir d'inviter les participants,
industriels et académiques, à présenter des démonstrations de logiciels et/ou de
prototypes qui s'appuient sur des méthodes de Traitement Automatique du Langage Naturel
pour le texte, la parole ou la langue des signes.

Dans ce cadre, les professionnels de l'industrie peuvent faire acte de candidature pour
présenter leur logiciel au cours d?une session dédiée. L'objet de cette dernière est
d'offrir un cadre d'interaction entre les milieux industriel et académique.

La session Démonstration académique et industrielle, accueillera des présentations sous
les formes suivantes (selon les besoins et disponibilités) :
- stand d'exposant ;
- poster de présentation ;
- démonstration de produits logiciels.

Pour participer, les candidats devront soumettre un résumé (2 pages) au format de la
conférence, en suivant les modalités indiquées ci-après. Le titre de l?article devra
commencer par : [JEP-TALN DEMO].


*Critères de sélection*

Les participants seront choisis par le comité d'organisation, indépendamment du processus
de sélection scientifique habituel. Les critères de sélection s'appuient sur la
pertinence des outils au regard des thématiques affichées par les conférences TALN et JEP.


*Modalités de soumission*

Les soumissions, au format PDF, doivent être conformes aux instructions de mise en page
qui seront disponibles dans les fichiers de style:
http://jep-taln2020.loria.fr/soumissions/

Site web de soumission des articles :
https://easychair.org/conferences/?conf=jeptalnrecital2020

Les soumissions en anglais sont acceptées dès lors qu'un co-auteur n?est pas francophone.

Le processus de relecture étant en double aveugle, les contributions ne doivent inclure
ni les noms ni les affiliations des auteurs, académiques ou industrielles. Les
auto-références et les noms de projets qui révèlent l'identité des auteurs, comme par
exemple, « Nous avons déjà démontré (Martin, 1991) » sont à proscrire. Les auteurs
doivent ainsi privilégier les citations telles que « Martin a précédemment démontré
(Martin, 1991) ». Les remerciements seront omis dans la première soumission, et pourront
être ajoutés dans la version définitive de l'article en cas d'acceptation.


*Dates importantes*

Date limite de soumission : 13 mars 2020
Notification aux auteurs : 27 mars 2020
Date limite de soumission des versions définitives : 24 avril 2020


*Comité de Programme*

Le comité de programme est présidé par Chloé Braud et David Langlois.

Contact : jep-taln-recital-2020@loria.fr

Back

Top

*Appel JEP-TALN?20 (JEP-TALN-RECITAL 2020)*

Conférence JEP 2020 | TALN 2020 | RÉCITAL 2020

8 au 12 juin 2020

Nancy, France

https://jep-taln2020.loria.fr/

La sixième édition conjointe de la conférence JEP-TALN-RECITAL sera organisée à Nancy du 8 au 12 juin 2020 (https://jep-taln2020.loria.fr/).

Cette année se tiendra, au sein de la conférence JEP-TALN, une session spéciale dédiée aux étudiant-e-s pré-doctorat ainsi qu?aux doctorant-e-s en 1re année. L?objectif principal est de permettre au maximum d?étudiant-e-s de participer à un premier événement scientifique d?ampleur afin d?éveiller des vocations pour la recherche, de favoriser les rencontres entre étudiant-e-s mais aussi entre étudiant-e-s et encadrant-e-s potentiel-le-s, ainsi qu?entre responsables de formations. Dans ce cadre, nous présentons un double appel.

Appel à communication - Projet étudiant

Les étudiant-e-s de Licence ou Master ont rarement l?occasion de participer à des conférences scientifiques ce qui pourrait pourtant encourager des vocations et mettre en contact étudiant-e-s et encadrant-e-s. Nous invitons les étudiant-e-s à venir présenter un projet réalisé au cours de l?année. La présentation sera faite sous forme de poster durant la conférence lors d?une session dédiée. Nous demandons aux étudiant-e-s intéressé-e-s de nous envoyer un descriptif d?une page maximum de leur projet. Le descriptif devra également préciser les noms du ou des étudiant-e-s, l?intitulé de la formation et les noms et affiliations du ou des encadrant-e-s. Ce projet doit s?inscrire dans l?un des domaines du traitement automatique des langues ou de l'étude de la parole. Le projet peut être porté par un ou plusieurs étudiant-e-s. 

Date limite de soumission : 10 avril 2020

Appel à communication - Ma thèse en 5 minutes

Les thèses reflètent les recherches actuelles menées par la communauté. Par ailleurs, il est important pour les étudiant-e-s de fréquenter des conférences le plus tôt possible, et de rencontrer les autres membres de la communauté. Nous invitons donc les étudiant-e-s en première année de thèse à venir présenter leur projet de thèse, à l?oral, dans un cadre bienveillant. Éventuellement, cette présentation pourra s?accompagner d?un poster présenté lors d?une session dédiée. Nous invitons les étudiant-e-s intéressé-e-s à nous envoyer un descriptif d?une page maximum décrivant la problématique générale de la thèse, le cadre général dans lequel elle s?inscrit et les principaux défis actuels auxquels ces travaux entendent répondre. Le descriptif devra également préciser les noms et affiliations du ou des encadrant-e-s. Le projet de thèse doit s?inscrire dans l?un des domaines du traitement automatique des langues ou de l'étude de la parole.  

Date limite de soumission : 10 avril 2020

Modalités de soumission

Les soumissions, au format PDF, doivent être conformes aux instructions de mise en page qui seront disponibles dans les fichiers de style: http://jep-taln2020.loria.fr/soumissions/

Site web de soumission des articles : https://easychair.org/conferences/?conf=jeptalnrecital2020, en utilisant la track dédiée ?Apprenti-e-s Chercheur-euse-s?.  

Les soumissions en anglais sont acceptées dès lors qu'un co-auteur n?est pas francophone.

Aides pour les étudiants

Afin d?encourager la venue des étudiant-e-s, nous proposons les aides suivantes :

• hébergement en résidence CROUS (tarifs à venir)

• inscriptions à tarifs réduits ?étudiants?, pensez à l?adhésion ATALA / AFCP !

• bourses pour les trajets : contactez les organisateurs 

Si vous souhaitez bénéficier de ces aides, merci de nous contacter au plus tôt, afin de nous permettre d?anticiper les besoins.

Contact : jep-taln-recital-2020@loria.fr

Back

Top

*Appel Tutoriels JEP-TALN'20  (JEP-TALN-RECITAL 2020)*
Conférence JEP 2020 | TALN 2020 | RÉCITAL 2020
8 au 12 juin 2020
Nancy, France
https://jep-taln2020.loria.fr/

Dans le cadre des conférences conjointes JEP-TALN-RECITAL organisées à Nancy
(https://jep-taln2020.loria.fr/), nous sollicitons des propositions de tutoriels. Les
tutoriels doivent porter sur une thématique particulière du TAL et du traitement
automatique ou l'étude de la parole. Les tutoriels sont l'occasion de former les
participants à des modèles, méthodes, techniques ou outils, nouveaux ou non, mais
présentant un intérêt pour la communauté.
Les organisateurs de JEP-TALN-RECITAL s?occuperont de la logistique (e.g. gestion des
salles, vidéo-projecteur, pauses café). Le responsable d'un tutoriel se chargera de la
communication sur celui-ci en partenariat avec les organisateurs des conférences.


*Dates importantes*

Les tutoriels auront lieu en parallèle le lundi 8 et mardi 9 juin 2020 sur le lieu de
conférence à Nancy. Ils pourront durer une demi-journée ou une journée.
  - Date limite de soumission de proposition de tutoriels : vendredi 10 janvier 2020
  - Notification aux candidats de la réponse aux propositions de tutoriels : vendredi 17
janvier 2020
  - Remise du programme des tutoriels (pour la publication dans le livret) : vendredi 24
avril 2020
  - Date des tutoriels : lundi 8 et mardi 9  juin 2020


*Modalités de proposition*

Les propositions comprendront :
- le nom du tutoriel,
- une description synthétique (max. 1 page A4 en format PDF) du thème du tutoriel (y
compris une justification de son affluence espérée), de son contenu, et du fonctionnement
attendu (présentations, TP, etc.)
- une brève présentation du ou des intervenants,
- la durée souhaitée du tutoriel (1 journée ou 1/2 journée).

Les propositions devront être envoyées sous forme électronique à l?adresse
:jep-taln-tutoriels-2020@loria.fr  avec pour entête de courriel :[Tutoriel JEP-TALN 2020
: <titre du tutoriel>].


*Modalités de sélection*

Les propositions seront examinées par des membres des comités de programme de JEP, TALN,
le bureau de l?AFCP et le CPERM de l'ATALA.

Les critères suivants seront considérés pour acceptation :
- l?adéquation aux thèmes de l'une ou l'autre des conférences,
- l?originalité de la proposition,
- l'affluence pouvant être espérée.


*Format*
Les tutoriels auront lieu en français (ou en anglais pour les non-francophones). Nous
invitons les intervenants à mettre le matériel utilisé lors du tutoriel (présentations,
codes, données, etc.) à disposition sur un site web.

Contacts :jep-taln-tutoriels-2020@loria.fr

Back

Top

*Appel à ateliers (JEP-TALN-RECITAL 2020)*
Conférence JEP 2020 | TALN 2020 | RECITAL 2020
8?12 juin 2020
Nancy, France
https://jep-taln2020.loria.fr/

Le LORIA, l'ATILF et l'INIST, travaillant dans les domaines de la parole
et du traitement automatique des langues écrites, parlées et signées,
organisent

  du 8 au 12 juin 2020,

  sur le campus Lettres et Sciences Humaines de l?université de
  Lorraine,

la sixième édition conjointe de la conférence JEP-TALN-RECITAL. Elle
regroupera :

- les 33es Journées d'Etudes sur la Parole (JEP),
- la 27e conférence sur le Traitement Automatique des Langues
  Naturelles (TALN),
- la 22e Rencontre des Étudiants Chercheurs en Informatique pour le
  Traitement Automatique des Langues (RÉCITAL).

Dans le cadre de la conférence jointe JEP-TALN-RECITAL 2020 qui sera
organisée à Nancy du 8 au 12 juin 2020 (https://jep-taln2020.loria.fr/),
nous sollicitons des*propositions d'ateliers*. Les ateliers doivent
porter sur des thématiques propres aux JEP, à TALN, ou communes à
JEP-TALN.

Chaque atelier a sa propre présidence et son propre comité de
programme. Le responsable de l?atelier est chargé de la communication
sur celui-ci, de l?appel à soumissions et de sa diffusion, et de la
coordination de son comité de programme. Pour les aspects
organisationnels, le responsable d'atelier sera en liaison avec les
organisateurs de JEP-TALN-RECITAL, et ces derniers auront en charge la
partie logistique (gestion des salles, pauses café et diffusion des
articles).

*Dates importantes*

Les ateliers auront lieu en parallèle le lundi 8 et le mardi 9 juin 2020
sur le lieu de conférence à Nancy. Ils pourront durer une demi-journée
ou une journée.

  * Date limite de soumission de proposition d'atelier : vendredi 10 janvier 2020
  * Notification aux candidats de la réponse aux propositions
    d'atelier : vendredi 17 janvier 2020
  * Remise des versions finales des articles acceptés dans les
    ateliers (pour la publication dans les actes) : vendredi 15 mai 2020
  * Date des ateliers : lundi 8 et mardi 9 juin 2020

*Modalités de soumission des propositions*

Les propositions d?ateliers devront être déposées sur le site web de
soumission (track ateliers) :
https://easychair.org/conferences/?conf=jeptalnrecital2020

Elles comprendront :
- le nom et l?acronyme de l?atelier,
- une description synthétique (au plus 1 page A4 en format PDF) du
  thème de l'atelier,
- le comité de programme (2 à 3 personnes chargées de la sélection
  finale des articles)
- la durée souhaitée pour la réalisation de l?atelier (1/2 ou 1
  journée).


*Modalités de sélection*

Les propositions d'atelier seront examinées par les membres des comités
de programme de JEP et TALN. Les critères suivants seront considérés
pour l'acceptation :

- l?adéquation aux thèmes de la conférence,
- l?originalité de la proposition.

On veillera à ce que les membres du comité de programme (lors de la
soumission) puis du comité de lecture soient équilibrés en terme de
genre et d'affiliations.

*Format*

Les conférences auront lieu en français ou en anglais pour les non
francophones.

Les articles soumis dans les ateliers devront suivre le format de TALN
2020 (nombre de pages à la discrétion du comité de programme de
l'atelier) :http://jep-taln2020.loria.fr/soumissions/

*Contacts*

Le comité de programme est présidé par Chloé Braud, David Langlois, Slim
Ouni et Sylvain Pogodalla.

Contact :jep-taln-ateliers-2020@loria.fr

Back

Top

*JEP'20 call for papers (JEP-TALN-RECITAL 2020)*
JEP 2020 Conference | TALN 2020 | RECITAL 2020
June 8-12, 2020
Nancy, France
https://jep-taln2020.loria.fr/

LORIA, ATILF and INIST are french laboratories and institutes located in Nancy and
working in the fields of speech and automatic processing of written, spoken and signed
languages. With the scientific support of the AFCP (Association Francophone pour la
Communication Parlée) and ATALA (Association pour le Traitement Automatique des Langues),
they are organizing the sixth joint edition of the JEP-TALN-RECITAL conference. It will
take place:

from 8 to 12 June 2020

on the Lettres et Sciences Humaines campus of the University of Lorraine in Nancy, France

This edition will therefore include:

- the 33rd Study Days on Speech (Journées d'Etudes sur la Parole - JEP),
- the 27th Conference on Natural Language Processing (Traitement Automatique des Langues
Naturelles - TALN),
- the 22nd Meeting of Student Researchers in Computer Science for Automatic Language
Processing (Rencontre des Étudiants Chercheurs en Informatique pour le Traitement
Automatique des Langues - RÉCITAL).

The JEP'2020 will include oral and poster presentations and invited lectures.

The official language of the conference is French.

*Types of contributions*

Authors are invited to submit two types of contributions:

- articles presenting original research work
- position papers presenting a point of view about spoken communication

Articles must present original works, with a substantial contribution compared to other
works that may already have been published. In the case of works already partially or
totally published in another language, the article should refer to the original
publication in a footnote.

Articles will be presented in the form of an oral presentation or a poster.

*JEP topics*

Contributions may cover all topics related to spoken communication and speech processing
in their various aspects, as well as their applications.

The topics of the conference include, but are not limited to:

- automatic speech processing
- transcription, synthesis, translation, dialogue,
- understanding, coding
- acquisition and learning
- production, perception and cognition
- health, disorders and disability
- phonetics, phonology, prosody
- geolinguistics and sociolinguistics
- resources and evaluation

*Selection criteria*

Submissions will be reviewed by at least two specialists of the field. For research work,
particular consideration will be given to:

- relevance to the conference topics
- importance and originality of the contribution
- correction of scientific and technical content
- critical analysis of the results, particularly in relation to other works in the field
- status of the work in the context of international research
- organization and clarity of the presentation

For position papers, preference will be given to:

- taking into account the state of the art and positioning in relation to it
- providing an original point of view
- demonstrating the potential impact of the position

The selected articles will be published in the conference proceedings.

*Submission instructions*

The articles will be written in French.

The size of the articles should not exceed 8 pages, plus one page dedicated to
bibliographic references.
A LaTeX style sheet, a Word template and a LibreOffice template are available on the
conference website: http://jep-taln2020.loria.fr/soumissions/

Submission website: https://easychair.org/conferences/?conf=jeptalnrecital2020

*Dates*

- Submissions due: 31 January 2020 (23:59 Paris time),
- Notification to authors: 03 April 2020
- Camera-ready due: 08 May 2020


*Scholarships*

The AFCP offers a number of scholarships for doctoral students and young researchers
wishing to attend the conference, see the AFCP website (http://www.afcp-parole.org/).

The ISCA also provides financial support to young researchers participating in scientific
events on speech and language, see the ISCA website
(https://www.isca-speech.org/iscaweb/).


*Contacts*

The JEP Program Committee is chaired by David Langlois and Slim Ouni.

Contact: jep-taln-ateliers-2020@loria.fr

 

Back

Top

Call for Papers,

Workshop on Laughter and Non-Verbal Vocalisations, Bielefeld,

15-16 June

the previous meetings held in Dublin (2012), Enschede
(2015), and Paris (2018), we have the pleasure to announce a
forthcoming workshop in Bielefeld.
Non-verbal vocalisations such as laughs, sighs, filled pauses, and
short utterances can communicate emotions and behavioural intentions.
Often, they also play an important role in regulating interactions.
The goal of this workshop is to bring together scientists from diverse
research areas and to provide an exchange forum for interdisciplinary
discussions in order to gain a better understanding of laughter and
other non-verbal vocalisations in multimodal human-human and
human-machine interactions. The workshop will consist of invited
talks, oral, and poster presentations of ongoing research.
We invite contributions from all relevant fields, including phonetics,
linguistics, psychology, conversation analysis, social signal
processing, and human-machine/robot interaction.

Submission procedure
???????
Researchers are invited to submit short papers or abstracts (max. 4
pages, including references) describing their work, including work in
progress. The submissions will be made available online.

Important dates
?????
* Submission portal opens: 15 December 2020
* Abstract submission deadline:  14 February 2020
* Notification acceptance/rejection:  31 March 2020
* Registration deadline by email: 01 June 2020
* Workshop dates: 15-16 June 2020

Venue
??
CITEC, Bielefeld University
https://cit-ec.de/en

Website
??-
Please check the website
http://bit.ly/laughterWorkshop
for updated information about the workshop


Programme Committee
???-

Nick Campbell - School of Linguistic, Speech and Communication
Sciences, Trinity College Dublin
Kevin El Haddad - University of Mons
Jonathan Ginzburg - University Paris Diderot
Dirk Heylen - Human Media Interaction, University of Twente
Bogdan Ludusan - Bielefeld University
Gary McKeown - Queen's University Belfast
Catherine Pelachaud - CNRS ? ISIR, Sorbonne University
Magdalena Rychlowska - Queen's University Belfast
Jürgen Trouvain - Computational Linguistics and Phonetics, Saarland University
Khiet Truong - Human Media Interaction, University of Twente
Petra Wagner - Bielefeld University


--

Back

Top

 Call for paper
========

Second ETeRNAL (Ethics and Natural Language Processing) workshop

Co-located with TALN 2020, on June 8th , 2020, Nancy, France

https://team.inria.fr/semagramme/eternal/

We are pleased to announce that the first ETeRNAL workshop will be held
on june 22nd, 2015 co-located with the TALN 2015 conference, in Caen
(Normandy), France.

Natural Language Processing (NLP) is a discipline at the heart of the
main ethical issues of this 21st century: access to personal data,
privacy protection, processing of big data, outsourcing and
crowdsourcing are all issues directly linked to the applications we
develop.

The issues we would like to be adressed concern both the contributions
of NLP and our ethical responsibilities as tool producers. We cannot
pretend not to know that NLP tools make abuses, crimes, violations of
individual rights possible. Today, what NLP tools are capable of? How
far is our moral responsibility involved? Should we be whistleblowers?
What could we do to limit the potentially negative effects of our
research?

Topics covered----------------------------------------------------------------------------
    - Sensitive data
    - Philosophical issues of Ethics and Data
    - Crowdsourcing and ethical issues
    - Ethical issues surrounding the use of tools or the result of processing
    - Quality and bias of the evaluation
    - Legal and economic issues
    - NLP for Ethics

Important
dates----------------------------------------------------------------------------
    Submission deadline:       March 13th 2020
    Notification:                       April 17th 2020
    Camera ready paper due: May 15th 2020
    Workshop:                         June 8th or 9th 2020

Submission----------------------------------------------------------------------------------
Articles shall be written in French for French speakers, in English for
those who do not speak French. They shall conform to JEP-TALN-RÉCITAL 2020
format and include between 4 to 8 pages.

Submissions, in PDF format, must conform to the template available here:
https://jep-taln2020.loria.fr/soumissions/

Article submission website :
https://easychair.org/conferences/?conf=jeptalnrecital2020
(Don't forget to link your submission to the ETeRNAL track.

Organizing commitee--------------------------------------------------------------------

    Gilles Adda, IMMI / LIMSI-CNRS
    Maxime Amblard, Université de Lorraine / LORIA
    Karën Fort, Université Paris 4 / STIH

Back

Top

• 10h00-10h30 : accueil - café
• 10h30 - 10h45 : introduction à la journée
• 10h45 - 11h45 : exposé invité Comparative Communicative Systems & the brain in primates: On the multimodal origin of language, Adrien Meguerditchian, Laboratoire de Psychologie Cognitive, CNRS/AMU, Marseille
• 11h45 - 13h45 : session posters de doctorants (voir ci-dessous) et repas
• 13h45 - 14h45 : exposé invité Toucher le Web pour mieux l'entendre... et l'écouter pour mieux le toucher, Fabrice Maurel, Université de Caen-Normandie, Greyc, Caen
• 14h45 - 15h45 : panel de discussion Quelle modalité pour faire passer un message ?
• 15h45 - 16h00 : Conclusions

Back

Top

• A brief description to explain why the challenge problem is important and relevant to the multimedia research community, industry, and society over the next 3-5 years or a longer horizon.
• A description of a specific set of research tasks or sub-tasks to be carried out towards tackling the challenge problem in the long run.
• An outline of current state-of-the-art techniques and why this Grand Challenge would help accelerate research in this important area.
• Link to sites containing relevant datasets to be used for objective training and evaluation of the grand challenge tasks. Full appropriate documentation on the datasets should be provided or made accessible.
• A description of rigorously defined objective criteria and/or procedures on how the submissions will be evaluated or judged.
• A commitment to publish and maintain a website related to their specific Grand Challenge containing the information, datasets, tasks for the Grand Challenge at least the next 3 years.
• Work with ACM Multimedia Conference organizers to publicize the Grand Challenge tasks to researchers for participation.
• Contact information of at least two organizers who will be responsible for organizing, publicizing, reviewing and judging the Grand Challenge submissions as described in the proposal.
• Note that although we ask organizers to express a multi-year commitment to their Grand Challenge, the Challenge will still undergo a new review each year. Priority will be given to Grand Challenges which have been successful in the past and are clearly contributing to continuity.

• Submission of Grand Challenge Proposals: 10 February 2020
• Notification of Acceptance: 24 February 2020
• Web Site and Call for Participation Ready: 10 March 2020
• Submission of solutions Grand Challenge: 29 June 2020 (required deadline)

• Lei Zhang (Microsoft, USA)

Back

Top

The French Research Network on Second Language Acquisition (RéAL2) helds its 3rd conference is held in Toulouse July 6/8 2020. We invite oral and poster presentations addressing all aspects of crosslinguistic influence in SLA and bilingualism. Please see attached document or consult our website: https://blogs.univ-tlse2.fr/real2-2020.

We are looking forward to your submission

Cecilia Gunnarsson
for the organisation committee of RéAL2 2020
Laboratoire Octogone-Lordat
Université de Toulouse ? Jean Jaurès

Back

Top

ACL 2020 Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML) 

Website: http://multicomp.cs.cmu.edu/acl2020multimodalworkshop/

Keynotes:

• Rada Mihalcea ? University of Michigan (USA)

• Ruslan Salakhutdinov ? Carnegie Mellon University (USA)

• M. Ehsan Hoque ? University of Rochester (USA)

• Yejin Choi - University of Washington (USA)

Important Dates 

• Paper Deadline: April 25th (Workshop) and May 1st (Grand-Challenge)

• Grand challenge test data release: Feb 15th

• Notification of Acceptance: May 9th

• Camera-ready: May 21st

• Workshop location: ACL 2020, Seattle, USA

**All deadlines @11:59 pm anywhere on Earth- year 2020)**

Supported by:

• National Science Foundation (NSF)

• Intel

=================================================================

The ACL 2020 Second Grand-Challenge and Workshop on Multimodal Language (ACL 2020) offers a unique opportunity for interdisciplinary researchers to study and model interactions between modalities of language, vision, and acoustic. Modeling multimodal language is a growing research area in NLP. This research area pushes the boundaries of multimodal learning and requires advanced neural modeling of all three constituent modalities. Advances in this research area allow the field of NLP to take the leap towards better generalization to real-world communication (as opposed to limitation to textual applications), and better downstream performance in Conversational AI, Virtual Reality, Robotics, HCI, Healthcare, and Education.

There are two tracks for submission: Grand-challenge and Workshop (workshop allows archival and non-archival submissions). Grand-Challenge is focused on multimodal sentiment and emotion recognition on CMU-MOSEI (grand-prize of >$1k in value for the winner) and MELD dataset. The workshop accepts publications in the below listed research areas. Archival track will be published in ACL workshop proceedings and non-archival track will be only presented during the workshop (but not published in proceedings). We invite researchers from NLP, Computer Vision, Speech Processing, Robotics, HCI, and Affective Computing to submit their papers.

• Neural Modeling of Multimodal Language

• Multimodal Dialogue Modeling and Generation

• Multimodal Sentiment Analysis and Emotion Recognition

• Language, Vision, and Speech

• Multimodal Artificial Social Intelligence Modeling

• Multimodal Commonsense Reasoning

• Multimodal RL and Control 

• Multimodal Healthcare

• Multimodal Educational Systems

• Multimodal Affective Computing

• Multimodal Robot/Computer Interaction

• Multimodal and Multimedia Resources

• Creative Applications of Multimodal Learning in E-commerce, Art, and other Impactful Areas.

We accept the following types of submissions:

• Grand challenge papers are 6-8 pages, including infinite references.

• Full and short workshop papers 6-8 and 4 pages respectively with infinite references. 

Submission must be formatted according to ACL 2020 style files: https://acl2020.org/calls/papers/#paper-submission-and-templates

Workshop Organizers

• Amir Zadeh (Language Technologies Institute, Carnegie Mellon University)

• Louis-Philippe Morency (Language Technologies Institute, Carnegie Mellon University)

• Paul Pu Liang (Machine Learning Department, Carnegie Mellon University)

• Soujanya Poria (Singapore University of Technology and Design)

Back

Top

Special Interest Group : Prosodic and phonetic features of speaking styles

at the PALA conference 2020 (Poetics and Linguistics Association), 15-18 July 2020, Aix-en-Provence, France

Call for Papers 

The PALA 2020 conference (https://pala.sciencesconf.org/) invites special interest groups (SIGs) this year, among which a session on prosodic and phonetic features of speaking styles (SIG 8). This special interest group will gather specialists in the oral language. The different styles of the written language clearly have several lexical and syntactic particularities. The styles of the spoken language are yet to be defined. We would like to investigate phonetic and prosodic phenomena from a stylistic point of view. Segmental aspects can be relevant in the characterisation of style. Phonetic variation will therefore be considered. Rhythm is also a crucial element: tempo, the degree of assimilation, elision and reduction. Intonation is another significant feature: are certain intonation patterns associated with certain speaking styles?

The special session will allow us to question the definition that can be given to phonostyle(s).

Papers from a wide range of theoretical perspectives addressing the above issues will be welcome. We invite studies based on ecological corpora as well as experimental studies.

Submission guidelines 

Please upload your abstracts (no more than 300 words, references included, no more than 5 references) on the web site of the conference before February 15 2020. Here is how to proceed: 

·       Go to  https://pala.sciencesconf.org/

·       Go to login, in the drop-down menu, select 'create an account? and create a login and password.

·       You?ll receive an activation email that will direct you to an authentication page. Enter your newly created username and password

·       On the website, click on MY SPACE and then on MY SUBMISSION (in the menu)

·       Fill in the title and abstract, select ?ABSTRACT?, and add keywords.

·       Make sure you indicate clearly that you wish your paper to be considered for a Special Interest Group (SIGs).

All abstracts for SIGs need to be sent via the website and copied to the SIG organizer (please send a doc file or a doc and pdf file if you have special fonts): sophie.herment@univ-amu.fr

Back

Top

International Conference on Signal Processing and Communications (SPCOM)

July 20-23, 2020; Indian Institute of Science, Bangalore

https://ece.iisc.ac.in/~spcom/2020/

Call for Papers

SPCOM provides a leading forum for researchers from academia, research laboratories, and industries to come together to share and learn about the current developments and emerging trends in the broad areas of signal processing and communications. SPCOM 2020 will be the thirteenth in the series of conferences and will feature several high-profile plenary talks, tutorials, talks by distinguished researchers from academia and the industry on topics of current interest.

Prospective authors are invited to submit original, high-quality research contributions (up to five pages long). The style files for preparing the manuscript are available on the conference website: https://ece.iisc.ac.in/~spcom/2020/index.html

Submitted manuscripts will go through double-blind peer-review. Accepted papers will appear in the conference proceedings, which will also be indexed on IEEE Xplore. Each accepted paper must be accompanied by a full registration and presented by one of the contributing authors. Each full registration can cover up to three accepted papers.

Topics of interest include, but are not limited to the following:

Wireless Communications

Cooperative and D2D Communications

MIMO and Space-Time Signal Processing

Cognitive Radio

Network Coding

Information Theory

Coding for Data Communications and Storage

Sensor Networks

Optical Communications and Networks

Next-Generation Networking and QoS

Cyber-Physical Systems

Multihop and Heterogeneous Networks

Vehicular Networks

THz and RF Systems for Communications

Green Communications

Energy and Smart Grid

Physical Layer Security

Detection and Estimation

Adaptive and Array Signal Processing

Compressive Sensing and Sparse Signal Processing

Signal Processing for Communications

Machine Learning for Signal Processing and Communications

Audio and Speech Signal Processing

Spoken Language Processing

Image and Video Signal Processing

Computational Imaging/Photography and Inverse Problems

Source Coding and Data Compression

Forensics and Security

Signal Processing Algorithms and Architectures

Underwater Communications and Signal Processing

VLSI for Communication and Signal Processing

Systems, Standards, and Implementations

Biological signal Processing

Biological Network and Data Analysis/Modeling

Deep Learning

Computer Vision

Natural Language Processing

Big Data

Autonomous Navigation and Robotics

Neuromorphic Systems 

Important dates:

Paper submission deadline: January 12, 2020

Acceptance notification: April 12, 2020

Camera-ready submission: May 10, 2020

Proposals for tutorials and special sessions will be by invitation only.

Team SPCOM 2020

Back

Top

4^th INTERNATIONAL SUMMER SCHOOL ON DEEP LEARNING
 
DeepLearn 2020
 
León, Guanajuato, Mexico
 
July 27-31, 2020
 
Co-organized by:
 
Center for Research in Mathematics, A.C. (CIMAT-CONACyT)
Guanajuato
 
Institute for Research Development, Training and Advice (IRDTA)
Brussels/London
 
https://deeplearn2020.irdta.eu/
 
***************************************************************
 
--- Early registration deadline: February 25, 2020 ---
 
***************************************************************
 
SCOPE:
 
DeepLearn 2020 will be a research training event with a global scope aiming at updating participants on the most recent advances in the critical and fast developing area of deep learning. Previous events were held in Bilbao, Genova and Warsaw.
 
Deep learning is a branch of artificial intelligence covering a spectrum of current exciting research and industrial innovation that provides more efficient algorithms to deal with large-scale data in neurosciences, computer vision, speech recognition, language processing, human-computer interaction, drug discovery, biomedical informatics, healthcare, recommender systems, learning theory, robotics, games, etc. Renowned academics and industry pioneers will lecture and share their views with the audience.
 
Most deep learning subareas will be displayed, and main challenges identified through 2 keynote lectures and 24 four-hour and a half courses, which will tackle the most active and promising topics. The organizers are convinced that outstanding speakers will attract the brightest and most motivated students. Interaction will be a main component of the event.
 
An open session will give participants the opportunity to present their own work in progress in 5 minutes. Moreover, there will be two special sessions with industrial and recruitment profiles.
 
ADDRESSED TO:
 
Master's students, PhD students, postdocs, and industry practitioners will be typical profiles of participants. However, there are no formal pre-requisites for attendance in terms of academic degrees. Since there will be a variety of levels, specific knowledge background may be assumed for some of the courses. Overall, DeepLearn 2020 is addressed to students, researchers and practitioners who want to keep themselves updated about recent developments and future trends. All will surely find it fruitful to listen and discuss with major researchers, industry leaders and innovators.
 
VENUE:
 
DeepLearn 2020 will take place in León, the most populous city in the state of Guanajuato, in central Mexico, and a major economic pole in the country with specialization in leather industry. The venue will be:
 
Poliforum León
Blvd. Adolfo López Mateos esq. Blvd. Francisco Villa
Col. Oriental, León, Gto., Mexico, C.P. 37510
 
STRUCTURE:
 
3 courses will run in parallel during the whole event. Participants will be able to freely choose the courses they wish to attend as well as to move from one to another.
 
KEYNOTE SPEAKER:
 
Maja Pantic (Imperial College London), Artificial Emotional Intelligence, Faces, Deep Fakes and Other Topics
 
PROFESSORS AND COURSES: (to be completed)
 
Rick S. Blum (Lehigh University), [introductory/intermediate] Deep Learning and Cybersecurity
 
Ben Brown (Lawrence Berkeley National Laboratory), [introductory/advanced] Explainable AI (XAI) Techniques for Science and Engineering -- Toward Statistical Inference for the 21st Century
 
Georgios Giannakis (University of Minnesota), [advanced] Ensembles for Interactive and Deep Learning Machines with Scalability, Expressivity, and Adaptivity
 
Ça?lar Gülçehre (DeepMind), [intermediate/advanced] Deep Reinforcement Learning
 
Vincent Lepetit (ENPC ParisTech), [intermediate] Deep Learning and 3D Geometry
 
Geert Leus (Delft University of Technology), [introductory/intermediate] Graph Signal Processing: Introduction and Connections to Distributed Optimization and Deep Learning
 
Andy Liaw (Merck Research Labs), [introductory] Deep Learning and Statistics: Better Together
 
Abdelrahman Mohamed (Facebook AI Research), [introductory/advanced] Recent Advances in Automatic Speech Recognition
 
Jan Peters (Technical University of Darmstadt), [intermediate] Robot Learning
 
Massimiliano Pontil (Italian Institute of Technology), [intermediate/advanced] Statistical Learning Theory
 
Jose Principe (University of Florida), [intermediate/advanced] Cognitive Architectures for Object Recognition in Video
 
Fedor Ratnikov (National Research University Higher School of Economics), [introductory] Specifics of Applying Machine Learning to Problems in Natural Science
 
Salim Roukos (IBM Research AI), [intermediate/advanced] Deep Learning Methods for Natural Language Processing
 
Björn Schuller (Imperial College London), [introductory/intermediate] Deep Signal Processing
 
Alex Smola (Amazon), [introductory/advanced] Dive into Deep Learning
 
Sargur N. Srihari (University at Buffalo), [introductory] Generative Models in Deep Learning
 
Kunal Talwar (Google Brain), [intermediate] Differentially Private Machine Learning
 
René Vidal (Johns Hopkins University), [intermediate/advanced] Mathematics of Deep Learning
 
Haixun Wang (WeWork), [introductory/intermediate] Conceptual Understanding and Machine Learning
 
Ming-Hsuan Yang (University of California, Merced), [intermediate/advanced] Learning to Track Objects
 
OPEN SESSION:
 
An open session will collect 5-minute voluntary presentations of work in progress by participants. They should submit a half-page abstract containing the title, authors, and summary of the research to david@irdta.eu by July 19, 2020.
 
INDUSTRIAL SESSION:
 
A session will be devoted to 10-minute demonstrations of practical applications of deep learning in industry. Companies interested in contributing are welcome to submit a 1-page abstract containing the program of the demonstration and the logistics needed. People participating in the demonstration must register for the event. Expressions of interest have to be submitted to david@irdta.eu by July 19, 2020.
 
EMPLOYER SESSION:
 
Firms searching for personnel well skilled in deep learning will have a space reserved for one-to-one contacts. It is recommended to produce a 1-page .pdf leaflet with a brief description of the company and the profiles looked for, to be circulated among the participants prior to the event. People in charge of the search must register for the event. Expressions of interest have to be submitted to david@irdta.eu by July 19, 2020.
 
ORGANIZING COMMITTEE:
 
Teresa Efigenia Alarcón Martínez (Guadalajara)
Oscar Dalmau Cedeño (Guanajuato, co-chair)
Sara Morales (Brussels)
Manuel J. Parra-Royón (Granada)
David Silva (London, co-chair)
 
REGISTRATION:
 
It has to be done at
 
https://deeplearn2020.irdta.eu/registration/
 
The selection of up to 8 courses requested in the registration template is only tentative and non-binding. For the sake of organization, it will be helpful to have an estimation of the respective demand for each course. During the event, participants will be free to attend the courses they wish.
 
Since the capacity of the venue is limited, registration requests will be processed on a first come first served basis. The registration period will be closed and the on-line registration tool disabled when the capacity of the venue is exhausted. It is highly recommended to register prior to the event.
 
FEES:
 
Fees comprise access to all courses and lunches. There are several early registration deadlines. Fees depend on the registration deadline.
 
ACCOMMODATION:
 
Suggestions for accommodation will be available in due time.
 
CERTIFICATE:
 
A certificate of successful participation in the event will be delivered indicating the number of hours of lectures.
 
QUESTIONS AND FURTHER INFORMATION:
 
david@irdta.eu
 
ACKNOWLEDGMENTS:
 
Centro de Investigación en Matemáticas, A.C. (CIMAT-CONACyT) ? Guanajuato
 
Centro Universitario de los Valles, Universidad de Guadalajara
 
Institute for Research Development, Training and Advice (IRDTA) ? Brussels/London

Back

Top

 EVALUATING MULTIMODAL DOCUMENTS
EMPIRICAL STUDIES ON THE UNDERSTANDING OF AUDIO-VISUAL TEXTS

Ielka van der Sluis
Gisela Redeker
Janina Wildfeuer

AILA 2020 CONGRESS

09-14 August 2020 • Groningen • The Netherlands

S051

EVALUATING MULTIMODAL DOCUMENTS

EMPIRICAL STUDIES ON THE UNDERSTANDING OF AUDIO-VISUAL TEXTS

Symposium | Call for Papers

Organisers

Ielka van der Sluis

Gisela Redeker

Janina Wildfeuer

multimodality • evaluation • reception • cognition

he symposium addresses how

multimodal analyses can be used for

and applied to the evaluation of

multimodal communication. It aims at

reviewing evaluation methods and

providing practical implications for the

design of accessible audio-visual texts.

While the use of multimodal resources

such as pictures, texts, sound and

moving images has become normal in

our communication, it is not self-evident

how these resources should effectively

be combined to guarantee the

envisioned understanding. Insights in

human processing principles and

empirical reception studies are needed

to evaluate multimodal design and to

inform the variety of theories and

methods in our broad multimodal

context.

The symposium concentrates on the

principles that underlie successful

communication by explicitly asking for

results from empirical reception studies

conducted with readers/users of

multimodal texts. We seek contributions

reporting empirical and corpus-based

studies of multimodal artefacts that

provide insights into how people

navigate an understand them.

Featured talks by Jana Holsanova, Lund

University, and James Pustejovsky,

Brandeis University, will provide

excellent starting points for our

discussions.

The symposium aims at gaining empirical and

theoretical insights into how readers and usersystematic empirical and corpus-based analyses and

that can provide practical implications for the design of

accessible audio-visual texts.

AILA 2020 CONGRESS

09-14 August 2020 • Groningen • The Netherlands

TYPES OF PRESENTATIONS

• Standard presentations

12-20-minute presentations with a ppt.

The exact amount of time for each of these

presentations is up to the symposium

organizers and depends on the number of

abstracts accepted.

• Focused presentations

In pitches of 2-5 minutes, speakers advertise

the presentations that take place in the

dedicated focused presentation space where

the symposia attendants meet during lunch

or drinks.

All the focused multimodal presentations

include a poster. Additionally, these

presenters will have the opportunity to

upload a full 12-minute version of their paper

(video/audio, ppt) to the AILA website for

exposure for a full year after presenting at

AILA 2020.

SUBMIT A PROPOSAL

Your submission will need to include the following:

• Author(s) and affiliation(s)

• Title: max. 20 words

• Abstract: max. 300 words

• Summary for program: max. 50 words

• Submit your paper proposal via the 'submit your paper'-link on

https://www.aila2020.nl/call-for-papers .

DATES

Submission deadline 16 September 2019

Notification by 18 November 2019

Back

Top

Call for Papers

The 13th edition of the Nordic Prosody (NP) conference series is proudly hosted by Centre of Industrial Electronics (CIE) at the University of Southern Denmark on science campus Alsion, Sonderborg, Denmark (https://www.sdu.dk/en/om_sdu/institutter_centre/centre+for+industrial+elektronics). The conference will be held as a satellite event to the 1st International Conference on Tone and Intonation (TAI), 16-20 August 2020. Note that there will be a discount for NP participants who sign up for both conferences!

The University of Southern Denmark (SDU) is both the third-largest and the third-oldest Danish university. Since the introduction of the ranking systems in 2012, the University of Southern Denmark has consistently been ranked as one of the top 50 young universities in the world by both the Times Higher Education World University Rankings and the QS World University Rankings. The SDU is also among the top 20 universities in Scandinavia.

Nordic Prosody conferences take place every 4 years. The first one was in Lund in 1978, organized by Eva Gårding, Gösta Bruce and Robert Bannert. The 12th Nordic Prosody was in 2016 in Trondheim, Norway. The conference series focuses on the forms and functions of prosodic patterns in Nordic languages and in languages spoken around the Baltic Sea. Contributions on all the various aspects of phonetics, phonology, and speech typology are welcome. Papers presenting new corpora, methods, or devices can be submitted as well. We also encourage researchers from neighboring disciplines like (second-language) pedagogy, acoustics, human-machine interaction, and voice pathology to submit contributions to the conference.

Keynote Speakers

***************

- David House (KTH Stockholm, Sweden) & Gilbert Ambrazaitis (Linnaeus University, Sweden): The multimodal nature of prominence

- Wim van Dommelen (Norwegian University of Science and Technology, Trondheim, Norway): Interactions of segmental and prosodic parameters

- Nicolai Pharao (Copenhagen University, Denmark): Processing prosody – recognizing speakers and recognizing words

Important dates:

**************
31 May 2020 Abstract submission deadline
21 June 2020 Early bird registration deadline
13-15 August 2020 13th Nordic Prosody Conference, Sonderborg, Denmark

01 November 2020 Full-paper submission deadline

Registrations are made through the conference website. Abstracts as well as full papers should be sent by email to np2020@sdu.dk. More detailed information about the formatting requirements will be available on the conference website.

http://www.prosody.dk

Conference proceedings will be published in a peer-reviewed volume of  a Peter Lang book series.

                                         NEW

two special sessions at Tone and Intonation 2020 (August 16-20, SDU Sonderborg), as described below.  Please visit www.tai2020.org for more information, now including the conference keynote speakers, registration information, etc.

“Perceptual impact of foreign accents and non-standard varieties”

Marta Ortega-Llebaria (University of Pittsburgh, USA) & Jan Volín (Charles University, Czech Republic)

Suprasegmental features of speech have received well-deserved attention in the past decades. In particular, research in the f0 domain has proven especially promising since the melodic and tonal attributes of speech are perceptually salient and robust. They also convey a variety of meanings – lexical, grammatical, affective, pragmatic, conative, social – and they facilitate cerebral speech processing and comprehension. Unprecedented mobility of human populations leads to multilingual contexts that create new situations of language contact and language learning involving typologically different language varieties, many of which are still under-researched. Exactly these new linguistic situations could provide new insights into functioning of melodic and tonal phenomena and their role in, for instance, the linguistic structure, language learning and social stereotyping.

Submissions that investigate tone and intonation in relation to the following subtopics are especially welcome:

• perception and interpretation of melodic and tonal features in non-native languages and non-standard varieties

• implicit (unconscious) judgements about the users of non-native languages and non-standard varieties

• explicit (conscious) evaluations of intonation of non-native languages and non-standard varieties in different contexts, e.g., court, L2 proficiency exams, job interviews, business presentations

• emotional response to non-standard varieties and foreign-accented speech

• social consequences of speaking outside standard

• effects of unfamiliar accents into f0 processing and cognitive load

• entrainment/conversational accommodation in f0 domain

• the role of intonation in perceived fluency, accentedness, intelligibility and comprehensibility

• didactic approach to tones and tunes in foreign language teaching

After the opening overview of the field, the special session is planned to host 6 oral presentations of 15 minutes plus 5 minutes for on-spot clarifications and a number of poster presentations. The presentations will be followed by a chaired panel discussion.

“Prosody-oriented studies of social communicative speech in a digitized world”

Barbara Schuppler (TU Graz, Austria) & Wentao Gu (Nanjing Normal University, China)

In the last decade, human-human and human-machine social communicative dialogues have received more and more attention among linguists and speech scientists. For one thing, linguists study social communicative speech in order to go beyond controlled experiments and get additional insights into how spoken languages are processed in dynamic interaction. For another thing, accurate and phenomenologically rich automatic speech/speaker/emotion recognition and expressive text-to-speech synthesis systems are essential for conversational dialogue systems, as these become increasingly more interactional and social rather than solely transactional. Prosody, as the major vehicle of social functions, plays key roles in both types of studies. The investigation of prosodic variation in dialogue does not only require applying existing methods to interactional data. It also requires developing new categories of forms and functions, new modeling techniques and new sources of data/knowledge. This special session aims at bringing together phoneticians, linguists and speech technologists interested in the prosody of conversational speech. Submissions on the following topics and on different languages, including minority languages, are especially welcome:

• tools and data resources for the annotation and analysis of prosody in conversational speech

• the relationship between prosodic forms and communicative functions

• cross-linguistic and individual prosody variation in social speech communication

• co-variation of the segmental and suprasegmental characteristics in speech communication

• models of prosody in conversational speech

• prosody-oriented studies in automatic speech/speaker/emotion recognition and expressive text-to-speech synthesis

• prosody-oriented studies in human-robot interaction

The special session is able to include a maximum of 10 submissions, e.g., subdivided into 7 oral presentations of 15 minutes plus 5 minutes for discussion and 3 oral presentations that showcase new methods, tools, and corpora.

Submissions to the special sessions use the same abstract and paper templates as regular contributions to TAI, and submissions are made through the same Easychair link as for regular contributions to TAI. The deadline for all submissions is 19 April 2020.  Please see www.tai2020.org for more information.

--------------------------------------------------------------------------------------------------------------

This mail was sent through the SProSIG mailing list, which is for

announcements of interest to the speech prosody research community.

To subscribe/unsubscribe, send mail to list@sprosig.org.

Nigel Ward, Professor of Computer Science, University of Texas at El Paso

CCSB 3.0408,  +1-915-747-6827

nigel@utep.edu    http://www.cs.utep.edu/nigel/   

We wish all of you a good start into the new lecture term.

The NP13 organizing committee,

Oliver Niebuhr, Jana Neitsch, Jan Michalsky, Meg Zellers, Stephanie Berger, Kerstin Fischer

Oliver Niebuhr

Associate Professor of Communication & Innovation

SDU Electrical Engineering

CIE - Centre for Industrial Electronics

This mail was sent through the SProSIG mailing list, which is for announcements of interest to the speech prosody research community. To subscribe/unsubscribe, mail list@sprosig.org.

Back

Top

The 28th European Signal Processing Conference (EUSIPCO 2020)

August 24-28, 2020, Amsterdam, The Netherlands

Website: http://2020.eusipco.org
=====================================================================

KEYNOTE SPEAKERS:

Rebecca Willett, Departments of  Statistics and Computer Science,
University of Chicago, USA.

Michael Unser, Biomedical Imaging Group, Ecole Polytechnique Fédérale
de Lausanne (EPFL), Switzerland.

Robert Heath, Department of Electrical and Computer Engineering,
University of Texas at Austin, USA.


CALL FOR PAPERS:

On behalf of the European Association for Signal Processing (EURASIP), it is a great
pleasure of the organizing committee to invite you to the 28th European Signal Processing
Conference, EUSIPCO 2020, to be held in Amsterdam, The Netherlands. EUSIPCO is the
flagship conference of EURASIP and offers a comprehensive technical program addressing
all the latest developments in research and technology for signal processing. EUSIPCO
2020 will feature worldclass speakers, oral and poster sessions, plenaries, exhibitions,
demonstrations, tutorials, and satellite workshops, and is expected to attract many
leading academic researchers and people from industry from all over the world.


TECHNICAL SCOPE:

We invite the submission of original, unpublished technical papers on topics including
but not limited to:

- Audio and acoustic signal processing
- Speech and language processing
- Image and video processing
   Multimedia signal processing
- Signal processing theory and methods
- Sensor array and multichannel signal processing
- Signal processing for communications
- Radar and sonar signal processing
- Signal processing over graphs and networks
- Nonlinear signal processing
- Statistical signal processing
- Compressed sensing and sparse modelling
- Optimization methods
- Machine learning
- Bio-medical image and signal processing
- Signal processing for computer vision and robotics
- Computational imaging / spectral imaging
- Information forensics and security
- Signal processing for power systems
- Signal processing for education
- Bioinformatics and genomics
- Signal processing for big data
- Signal processing for the internet of things
- Design/implementation of signal processing systems

Accepted papers will be included in IEEE Xplore©. EURASIP enforces a ?no-show? policy.
Procedures to submit papers, proposals for special sessions, tutorials and satellite
workshops can be found on the website.


VENUE:

Beurs van berlage (https://beursvanberlage.com). The Beurs van Berlage breathes history
and character. It was already a bustling trading place in 1903. Today it?s a one in a
million conference location in the warm heart of Amsterdam, with high quality and
service, an impressive atmosphere and excellent facilities. A fantastic location
that you?ll never forget! The building is located in the characteristic historic center
of Amsterdam, opposite the Central Station and around the corner from Dam Square. Amidst
impressive cultural highlights and no fewer than eight thousand hotel rooms. The design
by master architect Berlage breathes history and vigor. It certainly leaves
an unforgettable impression! In less than fifteen minutes from Schiphol Airport you?re
already in the Beurs van Berlage. Moreover, there are ample parking opportunities within
walking distance.


IMPORTANT DATES:

- Special Session Proposals? December 6, 2019
- Tutorial Proposals ? January 17, 2020
- Satellite Workshop Proposals ? January 24, 2020
- Full Paper Submission ? March 2, 2020
- Notification of Acceptance ? May 29, 2020
- Final Manuscript Submission ? June 12, 2020

Back

Top

1^st Call for paper – RO-MAN 2020 Special Session in Dialogue Management Systems for Human-Robot Interaction

The Special Session Dialogue Management Systems for Human-Robot Interaction will be held in Naples during the RO-MAN 2020 Conference (http://ro-man2020.unina.it/) which will take place from August 31^st to September 4^th. This Special Session is a joint initiative of Associazione Italiana di Linguistica Computazionale (AILC) and Associazione Italiana di Scienze della Voce (AISV), i.e. the two Italian scientific societies on Computational Linguistics and Speech Sciences.

The Special Session will focus on Spoken Dialogue Systems, currently a leading topic in Social and Interactional Robotics. In this area some ongoing, often unresolved, issues, including accuracy in automatic speech recognition, naturalness of speech synthesis and complexity of semantic domain representation, are fast going toward a revolutionary turning point allowing researchers to concentrate on multimodal integration, spoken language understanding, and automatic evaluation of the speaker’s intents.

SUBMISSION

We invite participants to submit a 6 pages paper. Example submission topics include, but are not limited to:

· Speech and gesture interfaces for robotic interaction

· Spoken language understanding and domain semantic representation

· Specific vs general domain dialogue systems

· Dialogue state tracking

· Datasets for training dialogue systems

· User intent classification

· Vision, spatial representation, deixis, reference disambiguation

· Persuasive dialogue systems ed empathic strategies

· Dialogic corpora collection

· Dialogue Systems evaluation

· Modelling miscommunication and repair strategies

AUTHORS SHOULD ADHERE TO THE FOLLOWING STEPS FOR SUBMITTING THE PAPER (FOR INITIAL SUBMISSION):

1. Create an account: go to https://ras.papercept.net/, then PIN and fill out the form. Ask all your co-authors to do the same if they do not have an account on the system yet, write down the authors' PINs (this information is needed for manuscript processing purposes).

2. Go to Support Menu and depending on how you are preparing your paper, download a template: LaTeX or MS-Word, Use these templates/style files to create the paper and save in PDF format.

3. Upload the paper: go to https://ras.papercept.net/ and click on 'Submit a contribution to RO-MAN 2020'.

4. Submit (regular paper, special session paper).

5. Fill in the form presented on the next page (make sure to enter all author PINs created in Step 1).

Please note, that our conference policy requires that at least one of the authors of the contributing submission must pay the conference registration fee to upload the final camera ready. This is to ensure that at least one of the presenting authors will be registered to attend the conference and deliver the presentation. The link to the registration system will be available on the conference website soon.

*The proposal must be submitted via the Papercept submission site.*

If you have any questions about the special sessions proposal submission, please contact programchair@ro-man2020.org

IMPORTANT DATES

Submission Deadline: MARCH 15, 2020

Notification of Acceptance: MAY 27, 2020

Camera-ready deadline: JUNE 15, 2020

With kind regards,

On behalf of the Organizing Committee:

Francesco Cutugno – University of Naples ‘Federico II’

Barbara Gili Fivela – University of Salento

Bernardo Magnini – Fondazione Bruno Kessler

Back

Top

Call for Papers ? Text Mining and Applications (TEMA?20) Track of EPIA?20

TeMA 2020 will be held at the 20th Portuguese Conference on Artificial
Intelligence (EPIA 2020) taking place at Lisboa, Portugal, from 7th to
9th September 2020. This track is organized under the auspices of the
Portuguese Association for Artificial Intelligence (APPIA). EPIA 2020
URL: : https://epia2020.inesc-id.pt/

This announcement contains the following information:

[1] Track description; [2] Topics of interest; [3] Important dates;
[4] Paper submission; [5] Track fees; [6] Organizing Committee; [7]
Program Committee and [8] Contacts.

[1] Track Description
The 10th Track of Text Mining and Applications (TeMA 2020) is a forum
for researchers working in Human Language Technologies, i.e. Natural
Language Processing (NLP), Computational Linguistics (CL), Natural
Language Engineering (NLE), Text Mining (TM), Information Retrieval
(IR), and related areas.
        The most natural form of sharing knowledge is indeed through textual
documents. Especially on the Web, a huge amount of textual information
is openly published every day, on many different topics and written in
natural language, thus offering new insights and many opportunities
for innovative applications of Human Language Technologies.
        Following recent advances in general IA sub-fields such as NLP,
Machine Learning (ML) and Deep Learning (DL), text mining is now even
more valuable as tool for bridging the gap between language theories
and effective use of natural language contents, for harnessing the
power of semi-structured and unstructured data, and to enable
important applications in real-world heterogeneous environments. Both
hidden and new knowledge can be discovered by using text mining
methods, at multiple levels and in multiple dimensions, and often with
high commercial value.
Authors are invited to submit their papers on any of the issues
identified in section [2]. Revision of the papers will be double-blind
by the members of the Program Committee. All accepted papers will be
published by Springer in a volume of Springer?s Lecture Notes in
Artificial Intelligence (LNAI) corresponding to the proceedings of the
20th EPIA Conference on Artificial Intelligence, EPIA 2020.

[2] Topics of Interest
TM, NLP, and Social Media Content Analysis
?       Entity Recognition and Disambiguation
?       Relation Extraction
?       Analysis of Opinions, Emotions and Sentiments
?       Text Clustering and Classification
?       Machine Translation
?       Summarization
?       Word Sense Disambiguation
?       Co-Reference Resolution
?       Language Modeling
?       Syntax and Parsing
?       Distributional Models and Semantics
?       Multi-Word Units
?       Lexical Knowledge Acquisition
?       Spatio-Temporal Text Mining
?       Entailment and Paraphrases
?       Natural Language Generation
?       Language Resources: Acquisition and Usage
?       Cross-Lingual Approaches
?       Algorithms and Data Structures for Text Mining
Applications:
?       Information Retrieval and Information Extraction
?       Question-Answering and Dialogue Systems
?       Text-Based Prediction and Forecasting
?       Web Content Annotation
?       Computational Social Science
?       Computational Journalism
?       Health and Well-being
?       Big Data Analysis

 [3] Important dates
Paper submission deadline: April 15, 2020
Paper acceptance notification: May 31, 2020
Camera-ready deadline: June 15, 2020
        EPIA Conference: September 7-9, 2020(Lisboa, Portugal)

[4] Paper submission
Submissions must be full technical papers on substantial, original,
and previously unpublished research. Papers can have a maximum length
of 12 pages. All papers should be prepared according to the formatting
instructions of Springer LNAI series. Authors should omit their names
from the submitted papers, and should take reasonable care to avoid
indirectly disclosing their identity. References to own work may be
included in the paper, as long as referred to in the third person. All
papers should be submitted in PDF format through the conference
management website at: https://epia2020.inesc-id.pt/
Authors should consult Springer?s authors? guidelines and use their
proceedings templates, either for LaTeX or for Word, for the
preparation of their papers. Springer encourages authors to include
their ORCIDs in their papers. In addition, the corresponding author of
each paper, acting on behalf of all of the authors of that paper, must
complete and sign a Consent-to-Publish form. The corresponding author
signing the copyright form should match the corresponding author
marked on the paper. Once the files have been sent to Springer,
changes relating to the authorship of the papers cannot be made.

[5] Track Fees:
 Track participants must register at the main EPIA 2020 conference.

[6] Organizing Committee:
Joaquim Silva, DI ? FCT/UNL, Quinta da Torre, 2829-516 Caparica,
Portugal (Contact person).
Pablo Gamallo, Universidade de Santiago de Compostela, Praza do
Obradoiro, 0, 15705 Santiago de Compostela, A Coruña, Spain.
Paulo Quaresma, DI ? Uviversidade de Évora, Largo dos Colegiais 2,
7000-645 Évora, Portugal.
Irene Rodrigues., DI ? Uviversidade de Évora, Largo dos Colegiais 2,
7000-645 Évora, Portugal

[7] Program Committee:
Adam Jatowt ? Universit of Kioto, Japan
Alberto Diaz ? Universidade Complutense de Madrid, Spain
Alberto Simões ? Algoritmi Center - University of Minho, Portugal
Alexandre Rademaker ? IBM / FGV, Brazil
Altigran Silva ? Universidade Federal do Amazonas, Brasil
Antoine Doucet ? University of Caen, France
António Branco ? Universidade de Lisboa, Portugal
Béatrice Daille ? University of Nantes, France
Bruno Martins ? Instituto Superior Técnico ? Universidade de Lisboa, Portugal
Eric de La Clergerie ? INRIA, France
Fernando Batista ? Instituto Universitário de Lisboa, Portugal
Francisco Couto ? Faculdade de Ciências ? Universidade de Lisboa, Portugal
Gabriel Pereira Lopes ? Faculdade de Ciências e Tecnologia ?
Universidade Nova de Lisboa, Portugal
Gaël Dias ? University of Caen Basse-Normandie
Hugo Oliveira ? Universidade de Coimbra, Portugal
Iñaki Vicente - Language Technology, Elhuyar Foundation
Irene Rodrigues ? Universidade de Évora, Portugal
Jesús Vilares ? University of A Coruña, Spain
Joaquim Ferreira da Silva ? Faculdade de Ciências e Tecnologia ?
Universidade Nova de Lisboa
Katerzyna Wegrzyn-Wolska ? ESIGETEL, France
Luisa Coheur ? Universidade Técnica de Lisboa, Portugal
Manuel Vilares Ferro ? University of Vigo, Spain
Marcos Garcia - Universidade da Coruña, Spain
Mário Silva ? Instituto Superior Técnico ? Universidade de Lisboa, Portugal
Miguel Alonso ? Universidade da Coruña, Spain
Pablo Gamallo ? Faculdade de Filologia, Santiago de Compustela, Spain
Patricia Martín-Rodilla ? Universidade da Coruña, Spain
Paulo Quaresma ? Universidade de Évora, Portugal
Pavel Brazdil ? University of Porto, Portugal
Renata Vieira ? Universidade de Évora, Portugal
Sérgio Nunes ? Faculdade de Engenharia ? Universidade do Porto, Portugal

[8] Contacts
Joaquim Francisco Ferreira da Silva, DI/FCT/UNL, Quinta da Torre,
2829?516, Caparica, Portugal. Tel: +351 21 294 8536 (ext. 10732) ?
Fax: +351 21 294 8541 ? E?mail: jfs [at]fct [dot] unl [dot] pt

Back

Top

  ************************************************************
        TSD 2020 - PRELIMINARY ANNOUNCEMENT and CALL for WORKSHOPS
       ************************************************************

Twenty-third International Conference on TEXT, SPEECH and DIALOGUE (TSD 2020)
              Brno, Czech Republic, 8-11 September 2020
                    http://www.tsdconference.org/

The conference is organized by the Faculty of Informatics, Masaryk
University, Brno, and the Faculty of Applied Sciences, University of
West Bohemia, Pilsen.  The conference is supported by International
Speech Communication Association.

Venue: Brno, Czech Republic


TSD SERIES

TSD series 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.


CALL for SATELLITE WORKSHOP PROPOSALS

The TSD 2020 conference will be accompanied by one-day satellite workshops
or project meetings with organizational support by the TSD organizing
committee. The organizing committee can arrange for a meeting room at the
conference venue and prepare a workshop proceedings as a book with ISBN by
a local publisher. The workshop papers that will pass also the standard TSD
review process will appear in the Springer proceedings.  Each workshop is
a subject to proposal that should be sent to the contact e-mail
tsd2020@tsdconference.org ahead of the respective deadline.


TOPICS

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
    (morphological and syntactic analysis, synthesis and
    disambiguation, 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)

Papers on processing of languages other than English are strongly
encouraged.


KEYNOTE SPEAKERS



PROGRAM COMMITTEE

    Elmar Noeth, Germany (general chair)
    Rodrigo Agerri, Spain
    Eneko Agirre, Spain
    Vladimir Benko, Slovakia
    Archna Bhatia, United States
    Jan Cernocky, Czech Republic
    Simon Dobrisek, Slovenia
    Kamil Ekstein, Czech Republic
    Karina Evgrafova, Russia
    Yevhen Fedorov, Ukraine
    Carlos Ferra, Cuba
    Volker Fischer, Germany
    Darja Fiser, Slovenia
    Eleni Galiotou, Greece
    Bjorn Gamback, Norway
    Radovan Garabik, Slovakia
    Alexander Gelbukh, Mexico
    Louise Guthrie, USA
    Tino Haderlein, Germany
    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
    Denis Jouvet, France
    Maria Khokhlova, Russia
    Aidar Khusainov, Russia
    Daniil Kocharov, Russia
    Miloslav Konopik, Czech Republic
    Ivan Kopecek, Czech Republic
    Valia Kordoni, Germany
    Evgeny Kotelnikov, Russia
    Pavel Kral, Czech Republic
    Siegfried Kunzmann, Germany
    Nikola Ljubesic, Croatia
    Natalija Loukachevitch, Russia
    Bernardo Magnini, Italy
    Oleksandr Marchenko, Ukraine
    Vaclav Matousek, Czech Republic
    France Mihelic, Slovenia
    Roman Moucek, Czech Republic
    Agnieszka Mykowiecka, Poland
    Hermann Ney, Germany
    Juan Rafael Orozco-Arroyave, Colombia
    Karel Pala, Czech Republic
    Nikola Pavesic, Slovenia
    Maciej Piasecki, Poland
    Josef Psutka, Czech Republic
    James Pustejovsky, USA
    German Rigau, Spain
    Leon Rothkrantz, The Netherlands
    Anna Rumshisky, USA
    Milan Rusko, Slovakia
    Pavel Rychly, Czechia
    Mykola Sazhok, Ukraine
    Odette Scharenborg, The Netherlands
    Pavel Skrelin, Russia
    Pavel Smrz, Czech Republic
    Petr Sojka, Czech Republic
    Georg Stemmer, Germany
    Marko Robnik Sikonja, Slovenia
    Vitomir Struc, Slovenia
    Marko Tadic, Croatia
    Jan Trmal, Czechia
    Tamas Varadi, Hungary
    Zygmunt Vetulani, Poland
    Aleksander Wawer, Poland
    Pascal Wiggers, The Netherlands
    Yorick Wilks, United Kingdom
    Marcin Wolinski, Poland
    Alina Wroblewska, Poland
    Victor Zakharov, Russia
    Jerneja Zganec Gros, Slovenia


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.

Social events including a trip in the vicinity of Brno will allow
for additional informal interactions.


CONFERENCE PROGRAM

The conference program will include oral presentations and
poster/demonstration sessions with sufficient time for discussions of
the issues raised.


IMPORTANT DATES

April 10 2020 ............ Submission of abstracts
April 17 2020 ............ Submission of full papers
June 5 2020 .............. Notification of acceptance
June 15 2020 ............. Final papers (camera ready) and registration
August 8 2020 ............ Submission of demonstration abstracts
August 15 2020 ........... Notification of acceptance for
                           demonstrations sent to the authors
September 8-11 2020 ...... 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.


OFFICIAL LANGUAGE

The official language of the conference is English.


ADDRESS

All correspondence regarding the conference should be
addressed to
   
    Ales Horak, TSD 2020
    Faculty of Informatics, Masaryk University
    Botanicka 68a, 602 00 Brno, Czech Republic
    phone: +420-5-49 49 18 63
    fax: +420-5-49 49 18 20
    email: tsd2020@tsdconference.org

The official TSD 2020 homepage is: http://www.tsdconference.org/tsd2020


LOCATION

Brno is the second largest city in the Czech Republic with a
population of almost 400.000 and is the country's judiciary and
trade-fair center. Brno is the capital of South Moravia, which is
located in the south-east part of the Czech Republic and is known
for a wide range of cultural, natural, and technical sights.
South Moravia is a traditional wine region. Brno had been a Royal
City since 1347 and with its six universities it forms a cultural
center of the region.

Brno can be reached easily by direct flights from London, Berlin and
Milano, and by trains or buses from Vienna (150 km) or Prague (230 km).

Back

Top

  TSD 2020 - FIRST CALL FOR PAPERS
         *********************************************************

Twenty-third International Conference on TEXT, SPEECH and DIALOGUE (TSD 2020)
              Brno, Czech Republic, 8-11 September 2020
                    http://www.tsdconference.org/

The conference is organized by the Faculty of Informatics, Masaryk
University, Brno, and the Faculty of Applied Sciences, University of
West Bohemia, Pilsen.  The conference is supported by International
Speech Communication Association.

Venue: Brno, Czech Republic


THE SUBMISSION DEADLINES:

    April 10 2020 ............ Submission of abstracts
    April 17 2020 ............ Submission of full papers

Submission of abstracts serves for better organization of the review
process only - for the actual review a full paper submission is
necessary.


KEYNOTE SPEAKERS

    Paolo Rosso, Universitat Politecnica de Valencia, Spain
    Diana Maynard, University of Sheffield, UK


TSD SERIES

TSD series 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. TSD Proceedings
are regularly indexed by Thomson Reuters Conference Proceedings Citation
Index.  Moreover, LNAI series are listed in all major citation databases
such as DBLP, SCOPUS, EI, INSPEC or COMPENDEX.


CALL for SATELLITE WORKSHOP PROPOSALS
https://www.tsdconference.org/tsd2020/conf_workshop_proposals.html

The TSD 2020 conference will be accompanied by one-day satellite workshops
or project meetings with organizational support by the TSD organizing
committee. The organizing committee can arrange for a meeting room at the
conference venue and prepare a workshop proceedings as a book with ISBN by
a local publisher. The workshop papers that will pass also the standard TSD
review process will appear in the Springer proceedings.  Each workshop is
a subject to proposal that should be sent via the proposal submission form
or discussed via the contact e-mail tsd2020@tsdconference.org ahead of the
respective deadline.


TOPICS

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
    (morphological and syntactic analysis, synthesis and
    disambiguation, 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, fake news 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)

Papers on processing of languages other than English are strongly
encouraged.


PROGRAM COMMITTEE

    Elmar Noeth, Germany (general chair)
    Rodrigo Agerri, Spain
    Eneko Agirre, Spain
    Vladimir Benko, Slovakia
    Archna Bhatia, USA
    Jan Cernocky, Czech Republic
    Simon Dobrisek, Slovenia
    Kamil Ekstein, Czech Republic
    Karina Evgrafova, Russia
    Yevhen Fedorov, Ukraine
    Carlos Ferra, Cuba
    Volker Fischer, Germany
    Darja Fiser, Slovenia
    Eleni Galiotou, Greece
    Bjorn Gamback, Norway
    Radovan Garabik, Slovakia
    Alexander Gelbukh, Mexico
    Louise Guthrie, USA
    Tino Haderlein, Germany
    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
    Denis Jouvet, France
    Maria Khokhlova, Russia
    Aidar Khusainov, Russia
    Daniil Kocharov, Russia
    Miloslav Konopik, Czech Republic
    Ivan Kopecek, Czech Republic
    Valia Kordoni, Germany
    Evgeny Kotelnikov, Russia
    Pavel Kral, Czech Republic
    Siegfried Kunzmann, USA
    Nikola Ljubesic, Croatia
    Natalija Loukachevitch, Russia
    Bernardo Magnini, Italy
    Oleksandr Marchenko, Ukraine
    Vaclav Matousek, Czech Republic
    France Mihelic, Slovenia
    Roman Moucek, Czech Republic
    Agnieszka Mykowiecka, Poland
    Hermann Ney, Germany
    Juan Rafael Orozco-Arroyave, Colombia
    Karel Pala, Czech Republic
    Nikola Pavesic, Slovenia
    Maciej Piasecki, Poland
    Josef Psutka, Czech Republic
    James Pustejovsky, USA
    German Rigau, Spain
    Leon Rothkrantz, The Netherlands
    Anna Rumshisky, USA
    Milan Rusko, Slovakia
    Pavel Rychly, Czechia
    Mykola Sazhok, Ukraine
    Odette Scharenborg, The Netherlands
    Pavel Skrelin, Russia
    Pavel Smrz, Czech Republic
    Petr Sojka, Czech Republic
    Georg Stemmer, Germany
    Marko Robnik Sikonja, Slovenia
    Vitomir Struc, Slovenia
    Marko Tadic, Croatia
    Jan Trmal, Czechia
    Tamas Varadi, Hungary
    Zygmunt Vetulani, Poland
    Aleksander Wawer, Poland
    Pascal Wiggers, The Netherlands
    Yorick Wilks, United Kingdom
    Marcin Wolinski, Poland
    Alina Wroblewska, Poland
    Victor Zakharov, Russia
    Jerneja Zganec Gros, Slovenia


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.

Social events including a trip in the vicinity of Brno will allow
for additional informal interactions.


SUBMISSION OF PAPERS

Authors are invited to submit a full paper not exceeding 8 pages
formatted in the LNCS style (including references). Those accepted
will be presented either orally or as posters. The decision about the
presentation format will be based on the recommendation of the
reviewers. The authors are asked to submit their papers using the
on-line form accessible from the conference website.

Papers submitted to TSD 2020 must not be under review by any other
conference or publication during the TSD review cycle, and must not be
previously published or accepted for publication elsewhere.

As reviewing will be blind, the paper 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 previously
showed (Smith, 1991) ...'.  Papers that do not conform to the
requirements above are subject to be rejected without review.

The authors are strongly encouraged to write their papers in TeX or
LaTeX formats. These formats are necessary for the final versions of
the papers that will be published in the Springer Lecture Notes.
Authors using a WORD compatible software for the final version must
use the LNCS template for WORD and within the submit process ask the
Proceedings Editors to convert the paper to LaTeX format.  For this
service a service-and-license fee of CZK 2000 will be levied
automatically.

The paper format for review has to be a PDF file with all required fonts
included. Upon notification of acceptance, presenters will receive further
information on submitting their camera-ready and electronic sources (for
detailed instructions on the final paper format see
http://www.springer.de/comp/lncs/authors.html#Proceedings, Sample File
typeinst.zip).

Authors are also invited to present actual projects, developed
software or interesting material relevant to the topics of the
conference.  The presenters of demonstrations should provide an
abstract not exceeding one page. The demonstration abstracts will not
appear in the conference proceedings.


IMPORTANT DATES

April 10 2020 ............ Submission of abstracts
April 17 2020 ............ Submission of full papers
June 5 2020 .............. Notification of acceptance
June 15 2020 ............. Final papers (camera ready) and registration
August 8 2020 ............ Submission of demonstration abstracts
August 15 2020 ........... Notification of acceptance for
                           demonstrations sent to the authors
September 8-11 2020 ...... Conference date

Submission of abstracts serves for better organization of the review
process only - for the actual review a full paper submission is
necessary.

The accepted conference contributions will be published in Springer
proceedings that will be made available to participants at the time
of the conference.


OFFICIAL LANGUAGE

The official language of the conference is English.


ACCOMMODATION

The organizing committee will arrange discounts on accommodation in
the 4-star hotel at the conference venue. The current prices of the
accommodation will be available at the conference website.


ADDRESS

All correspondence regarding the conference should be
addressed to
   
    Ales Horak, TSD 2020
    Faculty of Informatics, Masaryk University
    Botanicka 68a, 602 00 Brno, Czech Republic
    phone: +420-5-49 49 18 63
    fax: +420-5-49 49 18 20
    email: tsd2020@tsdconference.org

The official TSD 2020 homepage is: http://www.tsdconference.org/


LOCATION

Brno is the second largest city in the Czech Republic with a
population of almost 400.000 and is the country's judiciary and
trade-fair center. Brno is the capital of South Moravia, which is
located in the south-east part of the Czech Republic and is known
for a wide range of cultural, natural, and technical sights.
South Moravia is a traditional wine region. Brno had been a Royal
City since 1347 and with its six universities it forms a cultural
center of the region.

Brno can be reached easily by direct flights from London and Milan, and by
trains or buses from Vienna (150 km) or Prague (230 km).

Back

Top

Cognitive Aspects of the Lexicon

Workshop co-located with COLING
(28th International Conference on Computational Linguistics),
Barcelona, Spain, September 13, 2020

1 Background

Supporting us in many tasks (thinking, searching, memorizing and communicating) words are important. Hence, one may wonder how to build tools supporting their learning and usage (access/navigation). Alas the answer is not quite as straightforward as it may seem. It depends on various factors: the questioner's background (lexicography, psychology, computer science), the task (production/reception), and the material support (hardware). Words in books, computers and the human brain are not the same. Obviously, being aware of this, different communities have focused on different issues ?(dictionary building; creation of navigational tools; representation and organization of words; time course for accessing a word, etc.)? yet,  their views and  respective goals have changed considerably over time.  

Rather than considering the lexicon as a static entity, where discrete units (words) are organized alphabetically (database view), dictionaries are now viewed dynamically, i.e., as lexical graphs, whose entities are linked in various ways (topical relations; associations) and whose weight links may vary over time. While lexicographers view words as products (holistic entities), psychologists and neuroscientists view them as processes (decomposition), involving various steps or layers (representations) between an input and an output.

Computational linguists have their own ways to look at words, and their proposals have also changed quite a bit during the last decade. Discrete count-based vector representations have successively been replaced by continuous vectors (i.e., word embeddings) and then by language-model-based contextualized representations. These latter are more powerful than any of the other forms, as they are able to account for context ambiguity, outperforming the static models (including word-embeddings) in a broad range of tasks.

As one can see, different communities look at words from different angles, which can be an asset, as complementary views may help us to broaden and deepen our understanding of this fundamental cognitive resource. Yet, this diversity of perspectives can also a problem, in particular if the field is rapidly moving on, as in our case. Hence it becomes harder and harder for everyone, including experts, to remain fully informed about the latest changes (state of the art). This is one of the reasons why we organize this workshop. More precisely, our goal is not only to keep people informed without getting them crushed by the information glut, but also to help them to perceive clearly what is new, relevant, hence important. Last, but not least, we would like to connect people from different communities in the hope that this may help them to gain new insights or inspirations.

2   Scope and Topics

This workshop is about possible enhancements of lexical resources (representation, organization of the data, etc.). To allow for this we invite researchers to submit their contributions. The idea is to discuss the limitations of existing resources and to explore possible enhancements that take into account the users? and the engineers' needs (computational aspects).

Also, just like in the past we propose again a 'shared task'. This time the goal is to provide a common benchmark for testing lexical representations for the automatic identification of lexical semantic relations (synonymy, antonymy, hypernymy, part-whole meronymy) in various languages (English, Chinese, and so on).

For this workshop we solicit papers including but not limited to the following topics, each of which can be considered from various points of view: linguistics (lexicography, computational- or corpus linguistics), neuro- or psycholinguistics (tip-of-the-tongue problem, word associations), network-related sciences (vector-based approaches, graph theory, small-world problem), and so on.

1    Organization, i.e. structure of the lexicon
?     Micro- and macrostructure of the lexicon;
?     Indexical categories (taxonomies, thesaurus-like topical structures, etc.);
?     Map of the lexicon (topology) and relations between words (word associations).

2    The meaning of words and how to reveal it
?    Lexical representation (holistic, decomposed);
?    Meaning representation (concept based, primitives);
?    Distributional semantics (count models, neural embeddings, etc. )

3    Analysis of the conceptual input given by a dictionary user
?    What information do language producers typically provide when looking for a word (terms, relations)?
?    What kind of relational information do they give: typed or untyped relations?
?    Which relations are typically used?

4    Methods for crafting dictionaries or indexes
?    Manual, automatic or collaborative building of dictionaries and indexes (crowdsourcing, serious games, etc.);
?    Extraction of associations from corpora to build semantic networks supporting navigation;
?    (Semi-) automatic induction of the link type (e.g., synonym, hypernym, meronym, ...).

5    Creation of new types of dictionaries
?    Concept dictionary;
?    Dictionary of larger segments than words (clauses, phrasal elements);
?    Dictionary of patterns or concept-patterns;
?    Dictionary of syllables.

6    Dictionary access (navigation and search strategies), interface issues

?    Search based on sound (rhymes), meaning or contextually related words (associations);
?    Determination of appropriate search space based on the user?s cognitive state (information available at the onset: query) and meta-knowledge (knowledge concerning the relationship between the input and the target word), ...
?    Identification of typical word access strategies (navigational patterns) used by people;
?    Interface problems, data visualization.

3  Workshop Submissions

The workshop features two tracks: 

• A regular research track, where the submissions must be substantially original.
• A shared task track, with submissions consisting of system description papers.

The regular research track submissions should follow one of the 2 formats:

• Long papers (9 content pages + references) should report on solid and finished research including new experimental results, resources and/or techniques.
• Short papers (4 content pages + references) should report on small experiments, focused contributions, ongoing research, negative results and/or philosophical discussion.

Submissions must be anonymized, conform to the style sheet of COLING (https://coling2020.org/pages/call_for_papers), and be submitted via their website (https://www.softconf.com/coling2020/CogALex/). While some papers may be accepted only as posters, in the proceedings no distinction will be made between them and full papers.

4 Important Dates

       Workshop papers

• Paper submission deadline: May 14, 2020
• Notification of acceptance: June 24, 2020
•  Camera-ready papers due: July 11, 2020
• Workshop date: September 13, 2020

      
    Shared task

• Release of development data : March 1, 2020
• Release of test data April: 20-24, 2020 
• Announcement of winners May 1, 2020
• Shared task papers due: May 20, 2020

5 Invited Speaker

       Alex Arenas (http://deim.urv.cat/~alexandre.arenas/)

              Alephsys Lab, Computer Science & Mathematics,

              Universidad Rovira i Virgili, 43007 Tarragona, Spain

6 Workshop Organizers

• Michael Zock (LIS, CNRS, Aix-Marseille University, Marseille, France)
• Alessandro Lenci (Comput. Linguistics Laboratory, University of Pisa, Italy)
• Enrico Santus (MIT Computer Science& AI Lab, Boston, USA)
• Emmanuele Chersoni (Hong Kong Polytechnic University, Hong Kong, China)

7 Program Committee

see : https://sites.google.com/view/cogalex-2020/home/programme-committee

8 Contacts

For general questions, please get in touch with Michael Zock

e-mail:          michael.zock@lis-lab.fr

Homepage:   http://pageperso.lif.univ-mrs.fr/~michael.zock/

Concerning the shared task, please contact

Enrico Santus                 (esantus@gmail.com), or

Emmanuele Chersoni     (emmanuelechersoni@gmail.com)

Back

Top

News: The training data has been released. If you wish to access it, you need to register to the shared task here: https://forms.gle/LFsVaw6DqYikhKHx9

Held at COLING 2020 as part of the FNP-FNS 2020 workshop.

13 September, Barcelona, Spain.

====================

Shared Task URL: http://wp.lancs.ac.uk/cfie/fintoc2020/

Workshop URL: http://wp.lancs.ac.uk/cfie/fnp2020/

Participation Form: https://forms.gle/LFsVaw6DqYikhKHx9

Second Call for Participation

FinTOC?2 shared task


Held at COLING 2020 as part of the FNP-FNS 2020 workshop.
13 September, Barcelona, Spain.
====================


Shared Task URL: http://wp.lancs.ac.uk/cfie/fintoc2020/
Workshop URL: http://wp.lancs.ac.uk/cfie/fnp2020/
Participation Form: https://forms.gle/LFsVaw6DqYikhKHx9

_____________________________________________

The FinTOC?2 shared task aims to bring together the community of researchers interested in Financial Document Processing and Document Layout Analysis to advance the state of the art in the automatic processing of financial documents. This task focuses on the automatic generation of reports' Table Of Contents (henceforth TOC), as it is a key building block in the semantic analysis of financial documents. Generating the TOC requires detecting the span of all document sections and subsections, identifying their titles, and organising them into a hierarchy. It is a well-known fact that extracting document structure is a key step in information processing. For example sections can be used to determine areas where algorithms can be applied, such as Information Extraction, thus reducing false positives rate and irrelevant noise.

This is the second edition of the FinTOC shared task which will be held at COLING 2020 in Barcelona (Spain) as part of the FNP-FNS 2020 workshop. Last year?s edition received significant interest, particularly on the Title Detection track. Our aim this year is to increase interest by:
- lowering the barriers to the entry to the TOC extraction track, and
- opening up the task to a new language: French. We are particularly interested in systems which can be applied to both English and French languages.

This second edition proposes two tracks: one track per language, and it will score systems on both Title detection and TOC generation performance. We have revised the task and greatly simplified data formats to make it as smooth as possible for every interested researcher to participate and submit their systems? outputs at FinTOC?2.

Each of the participating teams will be asked to submit a short paper describing their methods and solutions to be presented at the workshop.

_____________________________________________

To register your interest in participating in FinTOC?2 shared task please use the following google form by no later than April 6th, 2020: https://forms.gle/LFsVaw6DqYikhKHx9
__________________________________________

Important dates:

December 1st, 2020: Registration opens.
February 17th, 2020: Release of training set & scoring scripts.
March 23rd, 2020: Release of test set.
April 6th, 2020: Registration deadline.
April 13th, Submission deadline.
May 1st, 2020: Release of results.
Sep 13th, 2020: Workshop day.
_________________________________________

Contact:
For any questions on the shared task please contact us on:
fin.toc.task@gmail.com
______________________________________


Shared task organizers:

- Najah-Imane Bentabet, Fortia Financial Solutions
- Ismail El Maarouf, Fortia Financial Solutions
- Mahmoud El-Haj, Lancaster University
- Remi Juge, Fortia Financial Solutions
- Dialekti Valsamou-Stanislawski, Fortia Financial Solutions

Back

Top

Call for Participation:

Back

Top

MLSP 2020

https://ieeemlsp.cchttps://ieeemlsp.cc https://ieeemlsp.cc

Call for Papers

Machine learning, as the driving force of this wave of AI, provides powerful solutions to many real-world technical and scientific challenges. The 30th MLSP workshop, an annual event organized by the IEEE Signal Processing Society MLSP Technical Committee, will present the most recent and exciting advances in machine learning for signal processing through keynote talks, tutorials, as well as special and regular single-track sessions. Prospective authors are invited to submit papers on relevant algorithms and applications including, but not limited to:

• Learning theory and modeling
• Neural networks and deep learning
• Bayesian Learning and modeling
• Sequential learning, sequential decision methods
• Information-theoretic learning
• Graphical and kernel models
• Bounds on performance
• Source separation and independent component analysis
• Signal detection, pattern recognition and classification
• Tensor and structured matrix methods
• Machine learning for big data
• Large scale learning
• Dictionary learning, subspace and manifold learning
• Semi-supervised and unsupervised learning
• Active and reinforcement learning
• Learning from multimodal data
• Resource efficient machine learning
• Cognitive information processing
• Bioinformatics applications
• Biomedical applications and neural engineering
• Speech and audio processing applications
• Image and video processing applications
• Intelligent multimedia and web processing
• Communications applications
• Other applications including social networks, games, smart grid, security and privacy

Special Session Call for Proposals

MLSP is seeking original, high quality proposals for Special Sessions, to be included in the technical program along with the regular track. Special Sessions are expected to address research in focused, emerging, or interdisciplinary areas of particular interest, not covered already by traditional MLSP sessions.

More details

Paper Submission

Prospective authors are invited to submit a double column paper of up to six pages using the electronic submission procedure which will be peer-reviewed.

More details

Paper Publication

Accepted papers will be published on on a password-protected website that will be available during the workshop. The presented papers will be published in and indexed by IEEE Xplore.

Schedule 2020

• Special session call deadline: March 19
• Paper submission deadline: April 19
• Decision notification: June 30
• Camera-ready paper deadline: July 25
• Advance registration deadline: August 22

Organizing Committee

General Chair: Simo Särkkä (Aalto University), Program Chairs: Lassi Roininen (Lappeenranta University of Technology), Andreas Hauptmann (University of Oulu), Manon Kok (TU Delft), Michael Riis Andersen (Technical University of Denmark), Finance Chair: Seppo Sierla (Aalto University), Publicity Chair: Arno Solin (Aalto University), Tutorial Chair: Alexander Ilin (Aalto University), Publications Chair: Roland Hostettler (Uppsala University), Advisory Committee: Zheng-Hua Tan (Aalborg University), Murat Akcakaya (University of Pittsburgh), Bhaskar Rao (University of California San Diego), Raviv Raich (Oregon State University)

Back

Top

*********************************************************

SPECOM-2020 – FIRST CALL FOR PAPERS

*********************************************************

22nd International Conference on Speech and Computer (SPECOM-2020)

Venue: St. Petersburg, Russia, October 06-10, 2020

Web: http://www.specom.nw.ru/2020

ORGANIZERS

The conference is organized by the St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences (SPIIRAS, St. Petersburg, Russia) in cooperation with Moscow State Linguistic University (MSLU, Moscow, Russia).

GENERAL CHAIRS

Alexey Karpov - SPIIRAS, Russia

Rodmonga Potapova - MSLU, Russia

CONFERENCE TOPICS

SPECOM attracts researchers, linguists and engineers working in the following areas of speech science, speech technology, natural language processing, human-computer interaction:

Affective computing

Audio-visual speech processing

Corpus linguistics

Computational paralinguistics

Deep learning for audio processing

Feature extraction

Forensic speech investigations

Human-machine interaction

Language identification

Multichannel signal processing

Multimedia processing

Multimodal analysis and synthesis

Sign language processing

Speaker recognition

Speech and language resources

Speech analytics and audio mining

Speech and voice disorders

Speech-based applications

Speech driving systems in robotics

Speech enhancement

Speech perception

Speech recognition and understanding

Speech synthesis

Speech translation systems

Spoken dialogue systems

Spoken language processing

Text mining and sentiment analysis

Virtual and augmented reality

Voice assistants

SATELLITE EVENT

5th International Conference on Interactive Collaborative Robotics ICR-2020: http://www.specom.nw.ru/icr2020

OFFICIAL LANGUAGE

The official language of the event is English. However, papers on processing of languages other than English are strongly encouraged.

FORMAT OF THE CONFERENCE

The conference program will include presentation of invited talks, oral presentations, and poster/demonstration sessions.

SUBMISSION OF PAPERS

Authors are invited to submit full papers of 6-10 pages formatted in the Springer LNCS style. Each paper will be reviewed by at least three independent reviewers (single-blind), and accepted papers will be presented either orally or as posters. Papers submitted to SPECOM 2020 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. The authors are asked to submit their papers using the on-line submission system: https://easychair.org/conferences/?conf=specom2020

PROCEEDINGS