|
 |
ISCApad #262 |
| Tuesday, April 14, 2020 by Chris Wellekens |
3 Events
| 3-1-1 | (2020-10-25) Cf Tutorials Interspeech 2020, Shanghai, China (UPDATE)
| |||||||||||||||||
| 3-1-2 | (2020-10-26) Cf Show and Tell, Interspeech 2020, Shanghai, China (UPDATED) Important Dates
? Submission deadline: Saturday, June 6, 2020 ? Acceptance/rejection notification: TBA ? Final paper and final video due: TBA INTERSPEECH is the world’s largest and most comprehensive conference on the science and technology of spoken language processing. Show & Tell is a special event organized during the conference. Participants are given the opportunity to demonstrate their most recent progress of developments, and interact with the conference attendees in an informal way, such as a demo, mock-up or any adapted format of their own choice. The contributions must highlight the innovative side of the concept and may relate to a regular paper. Submission and Preparation Guidelines Each initial Show & Tell submission must contain both a paper of up to 2 pages detailing the demonstration and a video illustrating what is going to be shown. The paper (including references) has to follow the format defined in the paper preparation guidelines as detailed in the “INTERSPEECH 2020 Author’s Kit”. Please note that the focus of the paper shall be on describing what the visitors will see and experience. The video can simply be recorded with a mobile phone or alike. Submissions will be evaluated by the organizing committee for relevance, originality, clarity, and significance of the proposed demonstration. At least one author of each accepted submission must register for and attend the conference, and demonstrate the system during the Show & Tell sessions. Each accepted Show & Tell paper will be allocated two pages in the conference proceedings. Furthermore, a final video, which is to be submitted by the final paper deadline, will be made publicly available. Show & Tell demonstrations will be presented in their dedicated time slot in the conference program. Each presentation space includes ? one poster board ? one table ? wireless internet connection, and ? a power outlet Please submit your proposal to the Show & Tell Chairs via show-and-tell@interspeech2020.org no later than June 6, 2020. QUESTIONS? PLEASE CONTACT our chair Ji Wu at show-and-tell@interspeech2020.org.
| |||||||||||||||||
| 3-1-3 | (2020-10-26) CfSS and challenges Interspeech 2020, Shanghai, China
| |||||||||||||||||
| 3-1-4 | (2020-10-26) First Voice Privacy Challenge at Interspeech 2020 UPDATED The deadlines for the First VoicePrivacy Challenge at Interspeech-2020 have been extended, and the schedule, including the submission deadline, has been adjusted according to the new Interspeech paper submission deadline of 8th May 2020. Also, version 1.2 of the VoicePrivacy 2020 Challenge Evaluation Plan is available on the challenge website: https://www.voiceprivacychallenge.org/docs/VoicePrivacy_2020_Eval_Plan_v1_2.pdf Changes include the same schedule update, the release of a second, simpler baseline system and results for both baselines. Both baselines are available online: https://github.com/Voice-Privacy-Challenge/Voice-Privacy-Challenge-2020 Please check the latest updates: https://github.com/Voice-Privacy-Challenge/Voice-Privacy-Challenge-2020/wiki/News-and-Updates The registration for the VoicePrivacy Challenge continues! Registration should be performed once for each participating entity and by sending an email to: organisers@lists.voiceprivacychallenge.org with ?VoicePrivacy 2020 registration? as the subject line. The mail body should include: (i) the name of the team; (ii) the name of the contact person; (iii) their country; (iv) their status (academic/nonacademic).
| |||||||||||||||||
| 3-1-5 | (2020-10-26) Interspeech 2020 Shanghai, China (UPDATED)
The submission and review process has also been updated as follows:
| |||||||||||||||||
| 3-1-6 | (2021-08-30) Interspeech 2021, Brno, Czech Republic INTERSPEECH 2021
| |||||||||||||||||
| 3-1-7 | Interspeech 2022, Incheon, South Korea Incheon in South Korea will welcome Interspeech 2022.
| |||||||||||||||||
| 3-2-1 | (2020-05-11) 1st Joint SLTU and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop, Marseille, France (MODIFIED DEADLINES) Call for Papers 1st Joint SLTU (Spoken Language Technologies for Under-resourced languages) and CCURL (Collaboration and Computing for Under-Resourced Languages) Workshop http://www.ilc.cnr.it/sltu-ccurl_2020/ 1st Call for Papers Date: 11-12 May, 2020. To be held as part of the 12th edition of the Language Resources and Evaluation Conference (LREC), at the Palais du Pharo, Marseille, France. Endorsed by SIGUL (http://www.elra.info/en/sig/sigul/) , ELRA and ISCA (to be confirmed) Invited speakers Alan Black, Carnegie Mellon University, USA Teresa Lynn, ADAPT Centre, Dublin City University, Ireland Tutorials On May 10th, SLTU-CCURL is pleased to offer two tutorials (held at Université Aixmarseille, near the LREC venue). T1: Jan Trmal, John Hopkins University (building ASR systems using the Kaldi toolkit) T2: Achim Rabus, University of Freiburg (Using Transkribus in training models for less-resourced languages) title to be confirmed More details will be announced on the workshop web page. Attendance to tutorials will be free of charge but registration will be required for organisational purposes (and number of attendees will be limited to 25 per tutorial). Workshop description and objectives The first joint SLTU-CCURL workshop will be held on May 11-12 2020 in Marseille, France, during LREC2020. Organized by SIGUL, a joint Special Interest Group of the European Language Resources Association (ELRA) and of the International Speech Communication Association (ISCA), this joint workshop will gather researchers working on speech processing and NLP for less resourced languages. We solicit papers and posters related to all areas of NLP , speech and computational linguistics, as well as those at the intersection with digital humanities and documentary linguistics, provided that they address lessresourced languages. Example topics are the following: -Language resource development, acquisition and representation -Linguistic theories, corpus development and resources -Linguistic and cognitive studies -Unsupervised discovery of linguistic units -Code switched lexical modeling -Multi-lingual and cross-lingual (spoken, text) language processing -Speech-to-text, text-to-speech and speech-to-speech processing -Machine translation and dialogue systems -NLP and speech technologies for under-resourced languages The intention of this joint SLTU-CCURL workshop is not only to provide a forum for the presentation of research, but also to offer a venue where researchers in different disciplines and varied backgrounds can fruitfully explore new areas of intellectual and practical development while honoring their common interest of sustaining less-resourced languages. We will have both oral presentation sessions and poster sessions. The decision on whether a presentation will be an oral or poster one will be taken by the Organizing Committee on the advice of the Program Committee, taking into account the subject matter and how that might be best conveyed. Oral and poster presentations will not be distinguished in the Proceedings. Submission and Publication ● Papers need to address less-resourced languages. They can contain an analysis and insight into existing methods and problems; a description of resources; an overview of the literature or of the current initiatives, or a combination of the above. Authors must declare if part of the paper contains material previously published elsewhere. ● Prospective authors are invited to submit full-length papers of 8 pages (references excluded), strictly complying with the LREC stylesheet (https:// lrec2020.lrec-conf.org/en/submission2020/authors-kit/). Papers should be submitted in PDF unprotected format to the workshop START page (URL will be provided in due time). ● Each submission will be reviewed by three programme committee members. In compliance with the LREC rules, papers must not be anonymized. Authors must declare if part of the paper contains material previously published elsewhere. ● Accepted papers will be presented either as oral presentations or posters and will be published in the workshop proceedings. ● The formatting template must be strictly adhered to and deadlines met. Important dates (Modified) 14 February 2020: Paper submission deadline February 14, 2020 Paper submission deadline March 13, 2020 Paper notification of acceptance April 2, 2020 Camera-ready papers due May 11-12, 2020 Workshop Identify, Describe and Share your LRs! ● Describing your LRs in the LRE Map is now a normal practice in the submission procedure of LREC (introduced in 2010 and adopted by other conferences). 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 Language Resource. The assignment of ISLRNs to LRs cited in LREC papers will be offered at submission time. Workshop chairs Dorothee Beermann, NTNU, Norway Laurent Besacier, LIG-Univ. Grenoble Alpes, France Sakriani Sakti, NAIST, Japan Claudia Soria, CNR-ILC, Italy Programme Committee ● Adrian Doyle (Galway University, Ireland) TBC ● Alexey Karpov (SPIIRAS, Russian Federation) ● Alexis Palmer (University of North Texas, USA) ● Amita Dev (BPIBS, India) TBC ● Amir Aharoni (Wikimedia Foundation) ● Andras Kornai (Hungarian Academy of Sciences, Hungary) ● Angelo Mario Del Grosso (CNR-ILC, Italy) ● Antti Arppe (University of Alberta, Canada) TBC ● Anupam Shukla (IIITM, India) ● Ayu Purwarianti (ITB, Indonesia) TBC ● Bruce Birch (The Minjilang Endangered Languages Publications Project, Australia) TBC ● Bruce Robertson (Mount Allison University, Canada) TBC ● Charl Van Heerden (SPbSU, Russian Federation) TBC ● Chiu Yu Tseng (ILAS, Taiwan) TBC ● Chris Cieri (LDC, USA) TBC ● Clara Rivera (Google) TBC ● Dafydd Gibbon (Bielefeld University, Germany) ● Delyth Prys (Bangor University, UK) ● Dewi Bryn Jones (Bangor University, UK) ● Dirk Van Compernolle (KU Leuven, Belgium) TBC ● Dorothee Beermann (NTNU, Norway) ● Emily Prud'hommeaux (Boston College, USA) TBC ● Emmanuel Dupoux (EHESS-ENS, France) TBC ● Federico Boschetti (CNR-ILC, Italy) ● Francis Tyers (Moscow Higher School of Economics, Russia) ● Gerard Bailly (GIPSA Lab, CNRS) TBC ● Gilles Adda (LIMSI/IMMI CNRS, France) TBC ● Hemant Patil (DA-IICT, India) ● Jeff Good (University at Buffalo, USA) ● John Judge (ADAPT DCU, Ireland) ● Jordan Lachler (University of Alberta, Canada) TBC ● Joseph Mariani (LIMSI-CNRS, France) TBC ● Karunesh Arora (C-DAC, NOIDA, India) TBC ● Kepa Sarasola (University of the Basque Country, Spain) TBC ● Kevin Scannell (Saint Louis University, Missouri, USA) ● Klara Ceberio (Elhuyar, Spain) ● Lane Schwartz (University of Illinois at Urbana-Champaign, USA) ● Laurent Besacier (LIG-IMAG, France) ● Lori Lamel (LIMSI, France) TBC ● Luong Chi-Mai (IOIT, Vietnam) TBC ● Maite Melero (Barcelona Supercomputing Center, Spain) ● Mans Hulden (University of Colorado Boulder, USA) TBC ● Maxim Romanov TBC ● Miikka Silfverberg (University of Helsinki, Finland) ● Mikel Forcada (Universitat d’Alacant, Spain) ● Mirna Adriani (UI, Indonesia) TBC ● Mohammad A. M. Abushariah (The University of Jordan, Jordan) ● Nick Thieberger (University of Melbourne / ARC Centre of Excellence for the Dynamics of Language, Australia) ● Omar Farooq (AMU, India) ● Pedro Moreno (Google, USA) TBC ● Pradip K Das (IIT, India) ● Richard Sproat (Google, USA) TBC ● Clara Rivera (Google) TBC ● Sakriani Sakti (NAIST, Japan) ● Satoshi Nakamura (NAIST, Japan) ● Sebastian Stüker (KIT, Germany) ● Shyam S Agrawal (KIIT, India) ● Sin Horng Chen (NCTU, Taiwan) ● Steven Bird (Charles Darwin University, Australia) TBC ● Tan Tien Ping (USM, Malaysia) TBC ● Tanja Schultz (Uni-Bremen, Germany) ● Thang Vu (Uni-Stuttgart, Germany) TBC ● Teresa Lynn (ADAPT Centre, Ireland) ● Trond Trosterud (Tromsø University, Norway) ● Tunde Adegbola (African Languages Technology Initiative, Nigeria) ● Uwe Springmann (Würzburg University, Germany) TBC ● Vera Ferreira (CIDLeS - Interdisciplinary Centre for Social and Language Documentation, Portugal) ● Win Pa Pa (UCS Yangon, Myanmar) ● Xavier Anguera (Telefonica, Spain) TBC ● Yoshinori Sagisaka (Waseda University, Japan) TBC ! Zuraida Mohd Don (UPSI, Indonesia) TBC Contact Laurent.Besacier@univ-grenoble-alpes.fr claudia.soria@ilc.cnr.it
| ||
| 3-2-2 | (2020-05-24) SProSIG conference, Tokyo, Japan (UPDATE) Two updates: As some of you are already aware, a new registration page is open.
Dear SProSIG members,
… update on the conference from https://sp2020.jpn.org/registration/ , in case you haven’t seen it already …
After careful consideration on the current and world-wide situations of COVID-19 and on uncertainty of the future situations, the organizing committee has made a decision to hold Speech Prosody 2020 as a virtual (online) conference, not to postpone the conference. A new registration page will open soon at the beginning of April.
All the authors are requested to submit a 15-min presentation video. The videos will be uploaded on YouTube and YouKu. More detailed information was already sent to authors of accepted papers.
Apr. 26 (AoE) Strict deadline to submit a presentation video Apr. 30 (AoE) Strict deadline for full registration to publish an accepted paper in the proceedings May 22 (AoE) Strict deadline for general registration
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/
Dear SProSIG members,
As previously announced, the next speech prosody conference will be held from May 24 to 28, 2020 at the University of Tokyo, Tokyo, Japan.
http://sp2020.jpn.org
The deadline for proposals for workshops, tutorials, and special sessions is Sep 15. If you have any interest in organizing such an activity, please send your proposal to office@sp2020.jpn.org.
We appreciate if you can circulate this also to your domestic speech prosody mailing lists.
Best wishes,
SP2020 chair Nobuaki MINEMATSU @ UTokyo office@sp2020.jpn.org
| ||
| 3-2-3 | (2020-05-24) The 10th Speech Prosody Conference, University of Tokyo, Tokyo, Japan (UPDATE)
Dear Speech Prosody SIG Members,
First, a brief note about SP 2020 in Tokyo: it will likely be a few more days before the registration page is open and the schedule posted, as the organizers are working out how best to deal with the travel disruptions the virus is causing. As information becomes available we’ll send it to this list.
In any case, looking ahead to 2022, members of SProSIG with a history of attendance at Speech Prosody conferences are encouraged to submit bids to host Speech Prosody 11. Bids submitted by April 21 will garner a presentation spot during Speech Prosody in Tokyo. The final deadline is June 30, 2020, and written bids received by that date will be posted at http://sprosig.org. The SProSIG membership will then be invited to consider the bids and to vote their preferences. Bids may include any information that you believe is likely to sway the members, but should contain at least:
- City and Country
- General Chair
- Organizing Committee Members
- Proposed conference dates
- Expected registration fee
- Sponsoring Organization (university, company, or agency; may be tentative)
- Venue (may be tentative)
- Access from the closest major airport
- Accommodation options
Further information and the bid template are available at http://sprosig.org/about.html. Please submit bids to Hongwei Ding (hwding@sjtu.edu.cn ) with a cc to Nigel Ward (nigelward@acm.org ).
Martine Grice, Plinio Barbosa, Aoju Chen, Hongwei Ding, Nigel Ward
Speech Prosody SIG Officers ******************************************************* The 10th Speech Prosody Conference will be held from May
| ||
| 3-2-4 | (2020-07-01) CfP SIGDIAL 2020 CONFERENCE, Boise, Idaho,USA (UPDATED) *Important information regarding COVID-19:
Dear SIGdial Community, We wanted to let everyone know our plans with regard to COVID-19. First, we want to reassure everyone that SIGDIAL 2020 will take place in some form, and papers accepted to SIGDIAL will be published. Since SIGDIAL 2020 is co-located with ACL in Seattle, we are coordinating our efforts with them. We are considering the possibility of either a virtual or a postponed conference. We will keep you posted on any updates regarding this decision. If you have any questions, don’t hesitate to contact us at conference@sigdial.org. Please take care of yourself and each other. Warmly, Gabriel Skantze, SIGdial President, in behalf of the SIGDIAL 2020 Organizing Committee SECOND CALL FOR PAPERS
SIGDIAL 2020 CONFERENCE
July 1-3, 2020
The 21st Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2020) will be held on July 1-3, 2020 at the Jack?s Urban Meeting Place (JUMP) in Boise, Idaho, USA. SIGDIAL will be temporally co-located with ACL 2020, which will be held on July 5-10 in Seattle, Washington, USA (https://acl2020.org/).
The SIGDIAL venue provides a regular forum for the presentation of cutting edge research in discourse and dialogue to both academic and industry researchers. Continuing a series of nineteen successful previous meetings, this conference spans the research interest areas of discourse and dialogue. The conference is sponsored by the SIGdial organization, which serves as the Special Interest Group in discourse and dialogue for both ACL and ISCA.
IMPORTANT DATES
IMPORTANT CHANGE FROM PREVIOUS CONFERENCES
Multiple Submission Policy: SIGDIAL no longer accepts papers that have been submitted to other meetings or journals whose review periods overlap with that of SIGDIAL.
TOPICS OF INTEREST
We welcome formal, corpus-based, implementation, experimental, or analytical work on discourse and dialogue including, but not restricted to, the following themes:
- Discourse Processing: Rhetorical and coherence relations, discourse parsing and discourse connectives. Reference resolution. Event representation and causality in narrative. Argument mining. Quality and style in text. Cross-lingual discourse analysis. Discourse issues in applications such as machine translation, text summarization, essay grading, question answering and information retrieval.
- Dialogue Systems: Open domain, task oriented dialogue and chat systems. Knowledge graphs and dialogue. Dialogue state tracking and policy learning. Social and emotional intelligence. Dialogue issues in virtual reality and human-robot interaction. Entrainment, alignment and priming. Generation for dialogue. Style, voice, and personality. Spoken, multimodal, embedded, situated, and text/web based dialogue systems, their components, evaluation and applications.
- Corpora, Tools and Methodology: Corpus-based and experimental work on discourse and dialogue, including supporting topics such as annotation tools and schemes, crowdsourcing, evaluation methodology and corpora.
- Pragmatic and/or Semantic Modeling: Pragmatics or semantics of discourse and dialogue (i.e., beyond a single sentence).
- Applications of Dialogue and Discourse Processing Technology
SUBMISSIONS
The program committee welcomes the submission of long papers, short papers and demo descriptions. Papers submitted as long papers may be accepted as long papers for oral presentation or long papers for poster presentation. Accepted short papers will be presented as posters.
- Long paper submissions must describe substantial, original, completed and unpublished work. Wherever appropriate, concrete evaluation and analysis should be included. Long papers must be no longer than 8 pages, including title, text, figures and tables. An unlimited number of pages is allowed for references. Two additional pages are allowed for appendices containing sample discourses/dialogues and algorithms, and an extra page is allowed in the final version to address reviewers? comments.
- Short paper submissions must describe original and unpublished work. Please note that a short paper is not a shortened long paper. Instead short papers should have a point that can be made in a few pages, such as a small, focused contribution; a negative results; or an interesting application nugget. Short papers should be no longer than 4 pages including title, text, figures and tables. An unlimited number of pages is allowed for references. One additional page is allowed for sample discourses/dialogues and algorithms, and an extra page is allowed in the final version to address reviewers? comments.
- Demo descriptions should be no longer than four pages including title, text, examples, figures, tables and references. A separate one-page document should be provided to the program co-chairs for demo descriptions, specifying furniture and equipment needed for the demo.
Authors are encouraged to also submit additional accompanying materials, such as corpora (or corpus examples), demo code, videos and sound files.
Multiple Submissions
SIGDIAL 2020 cannot accept work for publication or presentation that will be (or has been) published elsewhere and that have been or will be submitted to other meetings or publications whose review periods overlap with that of SIGDIAL. These restrictions apply only to refereed journals and meetings, not to unrefereed forums or workshops with a limited audience and without archival proceedings. Any questions regarding submissions can be sent to program-chairs[at]sigdial.org.
Blind Review
Building on previous year?s move to anonymous long and short paper submissions, SIGDIAL 2020 will follow the ACL policies for preserving the integrity of double blind review (see author guidelines). Unlike long and short papers, demo descriptions will not be anonymous. Demo descriptions should include the authors? names and affiliations, and
self-references are allowed.
Submission Format
All long, short, and demonstration submissions must follow the two-column ACL format. Authors are expected to use the LaTeX or Microsoft Word style template from the ACL conference (http://acl2020.org/downloads/acl2020-templates.zip [ acl2020. org/downloads/acl2020-templates. zip ] ). Submissions must conform to the official ACL style guidelines, which are contained in these templates. Submissions must be electronic, in PDF format.
Submission Link and Deadline
Authors have to fill in the submission form in the START system and upload a pdf of their paper before the March 6, 2020 deadline. https://www.softconf.com/l/sigdial2020/ ADOPTION OF ACL AUTHOR GUIDELINES
As noted above, SIGDIAL 2020 is adopting the ACL guidelines for submission and citation for long and short papers. Long and short papers that do not conform to the following guidelines will be rejected without review.
Preserving Double Blind Review
The following rules and guidelines are meant to protect the integrity of the double-blind reviewing process and ensure that submissions are reviewed fairly. The rules make reference to the anonymity period, which runs from 1 month before the submission deadline up to the date when your paper is either accepted, rejected or withdrawn.
- You may not make a non-anonymized version of your paper available online to the general community (for example, via a preprint server) during the anonymity period. By a version of a paper we understand another paper having essentially the same scientific content but possibly differing in minor details (including title and structure) or in length (e.g., an abstract is a version of the paper that it summarizes).
- If you have posted a non-anonymized version of your paper online before the start of the anonymity period, you may submit an anonymized version to the conference. The submitted version must not refer to the non-anonymized version, and you must inform the program chair(s) that a non-anonymized version exists. You may not update the non-anonymized version during the anonymity period, and we ask that you do not advertise it on social media or take other actions that would further compromise double-blind reviewing during the anonymity period.
- Note that, while you are not prohibited from making a non-anonymous version available online before the start of the anonymity period, this does make double-blind reviewing more difficult to maintain, and we therefore encourage you to wait until the end of the anonymity period if possible.
Citations and Comparison: If you are aware of previous research that appears sound and is relevant to your work, you should cite it even if it has not been peer-reviewed, and certainly if it influenced your own work. However, refereed publications take priority over unpublished work reported in preprints. Specifically:
Papers (whether refereed or not) appearing less than three months before the submission deadline are considered contemporaneous to your submission, and you are therefore not obliged to make detailed comparisons that require additional experimentation or in-depth analysis.
MENTORING
Acceptable submissions that require language (English) or organizational assistance will be flagged for mentoring, and accepted with a recommendation to revise with the help of a mentor. An experienced mentor who has previously published in the SIGDIAL venue will then help the authors of these flagged papers prepare their submissions for publication.
BEST PAPER AWARDS
In order to recognize significant advancements in dialogue/discourse science and technology, SIGDIAL 2020 will include best paper awards. All papers at the conference are eligible for the best paper awards. A selection committee consisting of prominent researchers in the fields of interest will select the recipients of the awards.
SIGDIAL 2020 ORGANIZING COMMITTEE
General Chair:
Olivier Pietquin, Google AI
Program Chairs:
Smaranda Muresan, Data Science Institute, Columbia University
Yun-Nung (Vivian) Chen, National Taiwan University
Local Chair:
Casey Kennington, Boise State University
Sponsorship Chair:
David Vandyke, University of Cambridge
Mentoring Chair:
Nina Dethlefs, University of Hull
Publication Chair:
Stefan Ultes, Daimler AG, Germany
SIGdial President:
Gabriel Skantze, KTH Royal Institute of Technology, Sweden
SIGdial Vice President:
Mikio Nakano, Honda Research Institute Japan, Japan
SIGdial Secretary:
Vikram Ramanarayanan, Educational Testing Service (ETS) Research, USA
SIGdial Treasurer:
Ethan Selfridge, Interactions, USA
SIGdial President Emeritus:
Jason Williams, Apple, USA
| ||
| 3-2-5 | (2020-07-01) CfSS SIGDIAL 2020, Boise, Idaho, USASIGDIAL 20201‐3 July, USA2nd Call for Special Sessions
The 21st Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL 2020) will be held on July 1-3, 2020 at the Jack’s Urban Meeting Place (JUMP) in Boise, Idaho, USA (http://www.sigdial.org/workshops/conference21/). Note the revised conference dates from previous announcement to avoid overlap with ICML 2020 and IJCAI 2020. SIGDIAL will be temporally co-located with ACL 2020, which will be held on July 5-10 in Seattle, Washington, USA (https://acl2020.org/).
IMPORTANT DATES Special Session Submission Deadline: January 15, 2020 Special Session Notification: January 31, 2020 To accommodate the conference date change, we moved the submission deadline slightly by 2 days. So please note the deadline of January 15, 2020.
The Special Interest Group on Discourse and Dialogue (SIGDIAL) organizers welcome the submission of special session proposals. We welcome special session proposals on any topic of interest to the discourse and dialogue communities. Topics of interest include, but are not limited to Role of Discourse in NLP Applications, Explainable AI, Evaluation, Annotation, and End‐to‐end systems. A SIGDIAL special session is the length of a regular session at the conference, and may be organized as a poster session, a panel session, a poster session with panel discussion, or an oral presentation session. Special sessions may, at the discretion of the SIGDIAL organizers, be held as parallel sessions. The papers submitted to special sessions are handled by the special session organizers, but for the submitted papers to be in the SIGDIAL proceedings, they have to undergo the same review process as regular papers. The reviewers for the special session papers will be taken from the SIGDIAL program committee itself, taking into account the suggestions of the session organizers, and the program chairs will make acceptance decisions. In other words, special session organizers decide what appears in the session, while the program chairs decide what appears in the proceedings and the rest of the conference program. Submissions Those wishing to organize a special session should prepare a two-page proposal containing: a summary of the topic of the special session; a list of organizers and sponsors; a list of people who may submit and participate in the session; and a requested format (poster/panel/oral session). These proposals should be sent to conference@sigdial.org by the special session proposal deadline. Special session proposals will be reviewed jointly by the general chair and program co‐chairs.
Links Those wishing to propose a special session may want to look at some of the sessions organized at recent SIGDIAL meetings. http://www.cs.utep.edu/nigel/deep/ https://www.sigdial.org/files/workshops/conference18/sessions.htm http://articulab.hcii.cs.cmu.edu/sigdial2016/ SIGDIAL 2020 Organizing Committee
General chair: Olivier Pietquin (Google Brain, France) Co-program chairs: Smaranda Muresan (Columbia University, USA) Yun-Nung Vivian Chen (National Taiwan University, Taiwan) Local chair: Casey Kennington (Boise State University, USA) Sponsorship chair: David Vandyke (Apple, UK) Mentoring chair: Nina Dethlefs (University of Hull, UK) Publication chair: Stefan Ultes (Mercedes-Benz Research & Development, Germany)
| ||
| 3-2-6 | (2020-08-16) 1st International Conference on Tone and Intonation (TAI), Sonderbedrg, Denmark (UPDATE) COVID 19: Till now the conference is maintained at the same place and date but we depend on Danish Government decisions. ***************** 'Tone and Intonation in a globalized, digital world' Sonderborg, Denmark 16-20 August 2020 The 1st edition of the Tone-and-Intonation (TAI) conference series is proudly hosted by the Centre of Industrial Electronics (CIE) at the University of Southern Denmark. Being a merger of the two former conference series TAL (Tonal Aspects of Languages) and TIE (Tone and Intonation in Europe), TAI 2020 welcomes contributions on phonetic and phonological analyses of prosody including (but not limited to) topics related to the production and perception of prosody and rhythm, the semantics and pragmatics of prosody, the acquisition and teaching of prosody in L1 and L2, and cross-linguistic comparisons of prosody. In addition, in TAI 2020 a number of sessions will be dedicated to the conference theme of globalization and digitization. In this context, we also encourage researchers of neighboring disciplines to submit papers related to tone and intonation to the conference. Globalization poses increasing challenges to both societies and individuals in terms of language contact and language acquisition. Digitization opens up new ways of human-human and human-machine interaction. In both contexts, tone and intonation are special linguistic, technical and didactic hurdles. Their better understanding not only has the potential for deeper insights into the nature of speech communication but can also decisively shape the communication of tomorrow. VENUE Centre of Industrial Electronics (CIE) at the University of Southern Denmark (SDU) on science campus Alsion, Sonderborg, Denmark (https://www.sdu.dk/en/om_sdu/institutter_centre/centre+for+industrial+elektronics). The 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. KEYNOTE SPEAKERS - Mariapaola D'Imperio (Rutgers University, USA) - Peggy Mok (The Chinese University of Hong Kong, China) - Stefan Baumann (University of Cologne, Germany) - Hans Basböll (University of Southern Denmark, Denmark)
01 March 2020 Online abstract submission opens 01 November 2020 Deadline for the submission of a revised abstract and an optional 5-page full paper (4 pages of text plus 1 page for references only) Registrations are made through the conference website. Abstract and paper submission will be handled via the EasyChair platform. More detailed information about the submission procedure and about the abstract/paper formatting requirements will be available on the conference website soon. TAI 2020 is co-sponsored by ISCA (International Speech Communication Association) and the IPA (International Phonetic Association). We are pleased to offer 5 IPA Student Awards that will cover the early bird student registration fee. Further ISCA-sponsored grants (max. 3) might be added soon. Please check the website tai2020.org for further information on how to apply. Oliver Niebuhr Associate Professor of Communication & Innovation SDU Electrical Engineering CIE - Centre for Industrial Electronics
| ||
| 3-2-7 | (2020-09-21) 11th International Workshop on Spoken Dialog System Technology (IWSDS2020), Madrid, Spain (UPDATED) The Information Processing and Telecommunications Center at Universidad Politécnica de Madrid (IPTC-UPM) in collaboration with Universidad de Granada are organizing the 11th International Workshop on Spoken Dialog System Technology (IWSDS2020) to be held in Madrid, Spain from September 21-23, 2020. We are now inviting paper submissions especially on the following topics:
However, submissions are not limited to these topics, therefore we are encouraging to submit papers in all areas of spoken dialogue systems. We particularly welcome papers that can be illustrated by a demonstration, and will organize the conference in order to best accommodate these papers, whatever their category. We distinguish between the following categories of regular submissions: Categories of submissions:
As usual, a selection of accepted papers will be published in a book by Springer following the conference (Springer LNEE series, SCOPUS and other important indexes).
Submission:Authors are requested to submit PDF files of their manuscripts using the paper submission system (EasyChair). IWSDS 2020 requires that all authors wishing to present a paper take into account:
NOTE: All submitted papers are subject to a single-blind review. The change in page limits is to accommodate responses to reviewer comments only.
Special Sessions and WorkshopsIn addition, IWSDS will host three special sessions and one workshop. Authors can submit specific papers to any of these using the same procedure as the regular papers but selecting the specific session during the submission process. For additional information about these special sessions and workshop please check the Special Session link:
Templates for formatting are available below:
Important datesPaper submission deadline: January 10, 2020 (23:59 Pacific Standard Time, GMT -8) Paper notification deadline: February 7, 2020 Camera ready papers due: February 21, 2020 Early bird registration ends: July 17, 2020 Website: https://www.iwsds.tech
Twitter: @iwsds2020
Supported by: SigDial and Colips
| ||
| 3-2-8 | (2020-09-21) CALL for Workshops and Special Sessions for IWSDS 2020, Madrid, Spain (UPDATED) CALL for Workshops and Special Sessions for IWSDS 2020 Place: Madrid, Spain
Dates: September 21-23, 2020
Website: https://www.iwsds.tech
INTERNATIONAL WORKSHOP ON SPOKEN DIALOG SYSTEM TECHNOLOGY (IWSDS) 2020 invites proposals for Workshops and Special Sessions in any topic related to the main conference theme: Conversational Dialogue Systems for the Next Decade. Authors are requested to submit PDF files (maximum three pages) of their proposal to iwsds2020@gmail.com The proposal must indicate:
Proposal submission deadline: September 13, 2019 Proposal acceptance notification: September 17, 2019 Important notice:
| ||
| 3-2-9 | (2020-09-21) CfW and SS: INTERNATIONAL WORKSHOP ON SPOKEN DIALOG SYSTEM TECHNOLOGY (IWSDS) 2020, Madrid Spain (UPDATED) The Information Processing and Telecommunications Center at Universidad Politécnica de Madrid (IPTC-UPM) in collaboration with Universidad de Granada are organizing the 11th International Workshop on Spoken Dialog System Technology (IWSDS2020) to be held in Madrid, Spain from September21-23, 2020. We are now inviting paper submissions especially on the following topics: List of Topics
However, submissions are not limited to these topics, therefore we are encouraging to submit papers in all areas of spoken dialogue systems. We particularly welcome papers that can be illustrated by a demonstration, and will organize the conference in order to best accommodate these papers, whatever their category. Submission GuidelinesAll papers must be original and not simultaneously submitted to another journal or conference.We distinguish between the following categories of regular submissions:
Authors are requested to submit PDF files of their manuscripts using the paper submission system (EasyChair). IWSDS 2020 requires that all authors wishing to present a paper take into account:
NOTE: All submitted papers are subject to a single-blind review. The change in page limits is to accommodate responses to reviewer comments only. As usual, a selection of accepted papers will be published in a book by Springer following the conference (Springer LNEE series, SCOPUS and other important indexes). Special Sessions and WorkshopsIn addition, IWSDS will host three special sessions and one workshop. Authors can submit specific papers to any of these using the same procedure as the regular papers but selecting the specific session during the submission process. For additional information about these special sessions and workshop please check the Special Session link:
Templates for formatting are available below: Important Dates
ContactAll questions about submissions should be emailed to iwsds2020@gmail.com SponsorsIWSDS2020 is sponsored by Universidd Politécnica de Madrid, SigDial, and Colips. CommitteesOrganizing Committee
Steering Committee
Senior Steering Committee
| ||
| 3-2-10 | The International Conference 'Language Technologies for All (LT4All): a report. The International Conference 'Language Technologies for All (LT4All):
|
| 3-3-1 | (2020-04-22) ESANN 2020: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges,Belgium (UPDATED) ESANN 2020: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning Bruges, Belgium, 22-23-24 April 2020
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
| |||||||
| 3-3-2 | (2020-05-04) 6th CHiME Speech Separation and Recognition Challenge, Barcelona, Spain (UPDATED) In response to the COVID-19 situation, the CHiME-2020 physical workshop in Barcelona has been cancelled and will be replaced with a virtual workshop online event. (See the full announcement on https://chimechallenge.github.io/chime2020-workshop). Details of the virtual event are currently being worked out and will announced on this site and via the CHiME forum. ----------------------------------------------
| |||||||
| 3-3-3 | (2020-05-04) ICASSP 2020, Barcelona, Spain (UPDATED)Announcing ICASSP 2020 as a Fully Virtual ConferenceThe safety and well-being of our participants is of paramount importance to IEEE Signal Processing Society. On 11 March 2020 the World Health Organization (WHO) declared Covid-19 a pandemic. After careful consideration and in light of the global health emergency and pervasive travel restrictions, IEEE Signal Processing Society has made the difficult decision to convert ICASSP 2020 to a fully virtual conference.We were looking forward to seeing everyone at ICASSP in Barcelona, but we are excited for the opportunity to innovate by creating an engaging virtual conference that will be rewarding for both presenters and attendees.Immediate guidance for authors, and questions about registration and participation are given below. We are actively discussing several options, with full details to be announced soon.Information for Authors of Accepted PapersBoth oral and poster papers will be presented by the author creating a 15-minute pre-recorded video within the virtual conference. This video will be required for each paper to be submitted for inclusion into IEEE Xplore. Authors will also be required to be available for a Q&A session on their paper. Authors that do not meet both these requirements will be considered 'no-shows.'We will provide more detailed instructions soon, particularly on how to record your presentations. In the interim, please do begin preparing your talk and associated visuals. Each should be timed carefully to not exceed the time allocation.Virtual Conference DatesThe conference will still take place between May 4-8, as these are the dates people have allocated to attend the conference. We expect most participants will still commit their time during this window to participate in the conference, and have discussions with fellow researchers around the world.Travel CancellationPlease review any previously confirmed travel, and proceed with contacting those providers for cancellation policies. You may want to consider the following advice:Flights:Many airlines are waiving the change fee on Non-Refundable Fare tickets provided you bought a ticket within a certain time window. Many airlines are also offering refunds if travel is cancelled due to the COVID-19 pandemic. Please check whether your preferred airline has enacted such policies. Please read carefully the fine print in any travel insurance you may have purchased as most plans will not cover cancellation of travel as a precautionary measure.Now Accepting Papers for ICASSP 2020The 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!
| |||||||
| 3-3-4 | (2020-05-11) Industry Track @ LREC 2020, Marseilles France Call for Paper: Industry Track @ LREC 2020 LREC Industry Track will take place within LREC 2020 in Marseille, France, May 11-16, 2020
| |||||||
| 3-3-5 | (2020-05-11) 13th WORKSHOP ON BUILDING AND USING COMPARABLE CORPORA (BUCC), Marseille, France ***** Upcoming deadlines *****
New submission deadline for regular papers: March 4, 2020
Participation in closed track of shared task: March 5, 2020
Participation in open track of shared task: March 15, 2020
Shared task system description papers: March 15, 2020
***************************************************************
13th WORKSHOP ON BUILDING AND USING COMPARABLE CORPORA (BUCC)
Co-located with LREC 2020, Pharo Palace, Marseille, France
Monday, May 11, 2020
SHARED TASK: Bilingual dictionary induction from comparable corpora
Website workshop: https://comparable.limsi.fr/bucc2020/
Website shared task: https://comparable.limsi.fr/bucc2020/bucc2020-task.html
Invited speaker: Holger Schwenk, Facebook AI Research
***************************************************************
MOTIVATION
In the language engineering and the linguistics communities, research in comparable corpora has been motivated by two main reasons. In language engineering, on the one hand, it is chiefly motivated by the need to use comparable corpora as training data for statistical NLP applications such as statistical and neural machine translation or cross-lingual retrieval. In linguistics, on the other hand, comparable corpora are of interest in themselves by making possible cross-language discoveries and comparisons. It is generally accepted in both communities that comparable corpora are documents in one or several languages that are comparable in content and form in various degrees and dimensions. We believe that the linguistic definitions and observations related to comparable corpora can improve methods to mine such corpora for applications of statistical NLP. As such, it is of great interest to bring together builders and users of such corpora.
TOPICS
We solicit contributions on all topics related to comparable corpora, including but not limited to the following:
Building Comparable Corpora:
* Human translations
* Automatic and semi-automatic methods
* Methods to mine parallel and non-parallel corpora from the web
* Tools and criteria to evaluate the comparability of corpora
* Parallel vs non-parallel corpora, monolingual corpora
* Rare and minority languages, across language families
* Multi-media/multi-modal comparable corpora
Applications of comparable corpora:
* Human translations
* Language learning
* Cross-language information retrieval & document categorization
* Bilingual projections
* Machine translation
* Writing assistance
* Machine learning techniques using comparable corpora
Mining from Comparable Corpora:
* Induction of morphological, grammatical, and translation rules from comparable corpora
* Extraction of parallel segments or paraphrases from comparable corpora
* Extraction of bilingual and multilingual translations of single words and multi-word expressions, proper names, and named entities from comparable corpora
* Induction of multilingual word classes from comparable corpora
* Cross-language distributional semantics
SUBMISSION INFORMATION
Please follow the style sheet and templates provided for the main conference at http://lrec2020.lrec-conf.org/en/submission/authors-kit/
Further details on the submission procedure are provided on the workshop website.
Papers should be submitted as a PDF file. Submissions must describe original and unpublished work and range from 4 to 8 pages excluding references.
Reviewing will be double blind, so the papers should not reveal the authors? identity. Accepted papers will be published in the workshop proceedings.
Double submission policy: Parallel submission to other meetings or publications is possible but must be immediately notified to the workshop organizers.
For further information see the BUCC 2018 website: http://comparable.limsi.fr/bucc2020/
In case of questions, please contact Reinhard Rapp: reinhardrapp (at) gmx (dot) de
IMPORTANT DATES
4 March 2020: New paper submission deadline
12 March 2020: Notification of acceptance
March 12, 2020: Early bird registration (reduced rates)
2 April, 2020: Camera ready final papers
May 11, 2020: Workshop date
SHARED TASK: BILINGUAL DICTIONARY INDUCTION FROM COMPARABLE CORPORA
In the framework of machine translation, the extraction of bilingual dictionaries from parallel corpora has been conducted very successfully. On the other hand, human second language acquisition appears not to be based on parallel data. This means that there must be a way of acquiring and relating lexical knowledge in two or more languages without the use of parallel data.
It has been suggested that it might also be possible to extract multilingual lexical knowledge from comparable rather than from parallel corpora. From a theoretical perspective, this suggestion might lead to advances in understanding human second language acquisition. From a practical perspective, as comparable corpora are available in much larger quantities than parallel corpora, this approach might help in relieving the data acqisition bottleneck which tends to be especially severe when dealing with language pairs involving low resource languages.
A well established practical task to approach this topic is bilingual lexicon induction from comparable corpora, which is in the focus of the current shared task. Typically, its aim is to extract word translations such as the following from comparable corpora:
English / French
baby bébé
baby poupon
bath bain
bed lit
bed plumard
convenience commodité
doctor médecin
doctor docteur
eagle aigle
mountain montagne
nervous nerveux
work travail
Quite a few research groups have been working on this problem using a wide variety of approaches. However, as there is no standard way to measure the performance of the systems, the published results are not comparable and the pros and cons of the various approaches are not clear.
The shared task aims at solving these problems by organizing a fair competition between systems. This is accomplished by providing corpora and evaluation datasets for a number of language pairs involving Chinese, English, French, German, Russian and Spanish and by comparing the results using a common evaluation framework. Other language pairs might be added on request.
Any submission to the shared task is expected to be accompanied by a system description paper (4 to 6 pages plus references). This will be accepted for publication in the workshop proceedings after a basic quality check.
Note that participation in the workshop, although we strongly encourage it, is not mandatory for participating in the shared task.
The shared task is divided in two tracks: One where the corpora provided by the organizers have to be used and another where participants can use their own data.
Further information on the shared task as well as the data sets is provided on the shared task website at https://comparable.limsi.fr/bucc2020/bucc2020-task.html
SHARED TASK SCHEDULE (see website for updates)
Any time: Expression of interest (not compulsory)
January 15, 2020: Release of shared task training sets
16 February 2020: Release of shared task test sets
5 March 2020: Submission deadline for shared task results (closed track)
15 March 2020: Submission of shared task system description papers
May 11, 2020: Workshop taking place at LREC 2020
For further information concerning the shared task see https://comparable.limsi.fr/bucc2020/ or contact reinhardrapp (at) gmx (dot) de
WORKSHOP AND SHARED TASK ORGANIZERS
Reinhard Rapp (Magdeburg-Stendal University of Applied Sciences and University of Mainz, Germany), Chair and contact person: reinhardrapp (at] gmx (dot) de
Pierre Zweigenbaum (Université Paris-Saclay,CNRS, Orsay, France)
Serge Sharoff (University of Leeds, United Kingdom)
PROGRAMME COMMITTEE
Ahmet Aker (University of Sheffield, UK)
Ebrahim Ansari (Institue for Advanced Studies in Basic Sciences, Iran)
Hervé Déjean (Naver Labs Europe, Grenoble, France)
Thierry Etchegoyhen (Vicomtech, Spain)
Silvia Hansen-Schirra (University of Mainz, Germany)
Hitoshi Isahara (Toyohashi University of Technology, Japan)
Kyo Kageura (The University of Tokyo, Japan)
Yves Lepage (Waseda University, Japan)
Sheervin Malmasi (Harvard Medical School, Boston, MA, USA)
Michael Mohler (Language Computer Corp., USA)
Emmanuel Morin (Université de Nantes, France)
Dragos Stefan Munteanu (Language Weaver, Inc., USA)
Ted Pedersen (University of Minnesota, Duluth, USA)
Reinhard Rapp (Magdeburg-Stendal University of Applied Sciences and University of Mainz, Germany)
Serge Sharoff (University of Leeds, UK)
Michel Simard (National Research Council Canada)
Richard Sproat (OGI School of Science & Technology, USA)
Pierre Zweigenbaum (LIMSI, CNRS, Université Paris-Saclay, Orsay, France)
INFORMATION FROM THE LREC ORGANIZERS
Please make sure that your papers take into account the following information about the LRE Map, the 'Share your LRs!' initiative and the ISLRN number:
Describing your LRs in the LRE Map is now a normal practice in the submission procedure of LREC (introduced in 2010 and adopted by other conferences). 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 Language Resource. The assignment of ISLRNs to LRs cited in LREC papers will be offered at submission time.
| |||||||
| 3-3-6 | (2020-05-11) LREC 2020, 12th Conference on Language Resources and Evaluation -Marseille, France, (UPDATE)
All registered participants who paid full fees before LREC Registration was suspended can now apply for refund by filling out the Refund Form by April 30, 2020.
In compliance with the new Refund policy , refund options are as follows:
1. I hold my registration: If the new dates for LREC (to be announced) do not suit me, I can decide to donate or to claim refund within one month after the announcement. In this case, the refund option will open again for one month even after the April 30, 2020 deadline.
2. I donate: Donations to ELRA are most welcome by the association to cope with the current situation and I decide just not to claim refund of my registration fees.
3. I claim refund of main conference fees: my main conference fees are partially refunded, only the organization costs incurred so far are retained : these costs are the same amount of the reduced fees for authors. My paper(s) accepted to the Main conference will be published in the LREC 2020 Proceedings.
4. I claim refund of my workshop/tutorial fees: my workshop and/or tutorial fees are fully refunded.
Please note that:
All refunds will be applied to the original method of payment (credit card, bank transfer). For payment by purchase order, we will be in contact with the institutions.
Requests submitted via email will NOT be processed. Please use the form.
All questions should be sent to registration@elda.org
DEADLINE EXTENSION March 19, 2020 (17:00 GMT+1) is the new deadline for registering to LREC 2020 at early-bird rate - registration@lrec-conf.org (registration) ********************************************************* LREC 2020, 12th Conference on Language Resources and Evaluation -
| |||||||
| 3-3-7 | (2020-05-13) REPROLANG (part of LREC Conference), Marseille , France FIRST CALL FOR PAPERS
| |||||||
| 3-3-8 | (2020-05-16) CfP LREC Workshop on Cross-Language Search and Summarization of Text and Speech, Marseille, France LREC Workshop on Cross-Language Search and Summarization of Text and Speech
| |||||||
| 3-3-9 | (2020-05-16) ONION: peOple in laNguage, visIOn and the miNd, Marseilles, France Third Call for Papers ONION: peOple in laNguage, visIOn and the miNd
Workshop to be held at the 12th Edition of the Language Resources and Evaluation Conference, Palais du Pharo, Marseilles, France, on Saturday, May 16 2020.
+++ New submission deadline: February 21, 2020 +++ We invite paper submissions for the first workshop on People in Language, Vision, and the Mind, which discusses how people, their bodies and faces as well as mental states are described in text. We are interested in contributions from diverse areas including language generation, language analysis, cognitive computing, affective computing. Detailed Workshop goals The workshop will provide a forum to present and discuss current research focusing on multimodal resources as well as computational and cognitive models aiming to describe people in terms of their bodies and faces, including their affective state as it is reflected physically. Such models might either generate textual descriptions of people, generate images corresponding to people?s descriptions, or in general exploit multimodal representations for different purposes and applications. Knowledge of the way human bodies and faces are perceived, understood and described by humans is key to the creation of such resources and models, therefore the workshop also invites contributions where the human body and face are studied from a cognitive, neurocognitive or multimodal communication perspective. Human body postures and faces are being studied by researchers from different research communities, including those working with vision and language modeling, natural language generation, cognitive science, cognitive psychology, multimodal communication and embodied conversational agents. The workshop aims to reach out to all these communities to explore the many different aspects of research on the human body and face, including the resources that such research needs, and to foster cross-disciplinary synergy.
The ability to adequately model and describe people in terms of their body and face is interesting for a variety of language technology applications, e.g., conversational agents and interactive multimodal narrative generation, as well as forensic applications in which people need to be identified or their images generated from textual or spoken descriptions.
Such systems need resources and models where images associated with human bodies and faces are coupled with linguistic descriptions, therefore the research needed to develop them is placed at the interface between vision and language research.
At the same time, this line of research raises important ethical questions, both from the perspective of data collection methodology and from the perspective of bias detection and avoidance in models trained to process and interpret human attributes.
By focussing on the modelling and processing of physical characteristics of people, and the ethical implications of this research, the workshop will explore and further develop a particular area within visual and language research. Furthermore, it will foster novel cross-disciplinary knowledge by soliciting contributions from different fields of research. By attempting to bring results from the cognitive and neurocognitive fields to the attention of the HLT community, it is also in line with the ?Language and the Brain? hot topic of LREC 2020.
Relevant topics
We are inviting short and long papers reporting original research, surveys, position papers, and demos. Authors are strongly encouraged to identify and discuss ethical issues arising from their work, insofar as it involves the use of image data or descriptions of people.
Relevant topics include, but are not limited to, the following ones:
Important dates Paper submission deadline:February 14, 2020 +++ New: February 21, 2020 +++
Notification of acceptance:March 13, 2020
Camera ready Papers:April 2, 2020
Workshop:May 16, 2020 (afternoon) Submission guidelines Short paper submissions may consist of up to 4 pages of content, while long papers may have up to 8 pages of content. References do not count towards these page limits. All submissions must follow the LREC 2020 style files, which are available for LaTeX (preferred) and MS Word and can be retrieved from the following address:https://lrec2020.lrec-conf.org/en/submission2020/authors-kit/ Papers must be submitted digitally, in PDF, and uploaded through the online submission system here: https://www.softconf.com/lrec2020/ONION2020/ The authors of accepted papers will be required to submit a camera-ready version to be included in the final proceedings. Authors of accepted papers will be notified after the notification of acceptance with further details. Identify, Describe and Share your LRs!
Describing your LRs in the LRE Map is now a normal practice in the submission procedure of LREC (introduced in 2010 and adopted by other conferences). 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 Language Resource. The assignment of ISLRNs to LRs cited in LREC papers will be offered at submission time.
Organisers
Patrizia Paggio, University of Copenhagen and University of Malta, paggio@hum.ku.dk
Albert Gatt, University of Malta, albert.gatt@um.edu.mt
Roman Klinger, University of Stuttgart, roman.klinger@ims.uni-stuttgart.de
Programme committee
Adrian Muscat, University of Malta
Andreas Hotho, University of Würzburg
Andrew Hendrickson, University of Tilburg
Catherine Pelachaud, Institute for Intelligent Systems and Robotics, UPMC and CNRS
Costanza Navarretta, CST, University of Copenhagen
David Hogg, University of Leeds
Diego Frassinelli, University of Stuttgart
Isabella Poggi, Roma Tre University
Jonas Beskow, KTH Speech, Music and Hearing
Jordi Gonzalez, Universitat Autònoma de Barcelona
Kristiina.Jokinen, National Institute of Advanced Industrial Science and Technology (AIST)
Mihael Arcan, National University of Ireland, Galway
Raffaella Bernardi, CiMEC Trento
Sebastian Padó, University of Stuttgart
Patrizia Paggio
Professor University of Malta Institute of Linguistics and Language Technology patrizia.paggio@um.edu.mt
| |||||||
| 3-3-10 | (2020-06-01) The 12th International Seminar on Speech Production (ISSP), Providence, RI, USA (UPDATED)
Important note: revised dates for conferenceBecause of disruptions associated with the COVID-19 pandemic the ISSP has been rescheduled for December 14th - 17th, 2020. Abstract submission has consequently been reopened; please see Instructions for Authors. Note that previously accepted abstracts do not need to be resubmitted; however, authors are encouraged to upload revised versions of their abstracts based on reviewer feedback using the EasyChair portal. The deadline for new submissions and revisions to accepted abstracts is August 1st, 2020. The 12th International Seminar on Speech Production (ISSP), organized through Haskins Laboratories, will take place June 1-4 2020 in Providence, RI, USA, at the Omni Convention Center Hotel. Inaugurated in Grenoble in 1988, the ISSP is an international forum for researchers to share their work on all aspects of human speech production, including phonology, phonetics, prosody, biomechanics, signal processing, motor control, neuroscience, modeling, disordered speech and speech accommodation. The diversity of topics is a particular strength of the conference, providing opportunities for young researchers especially to be exposed to complementary ideas and methods apart from their immediate focus. Previous meetings have occurred in Sydney, Ubatuba (Brazil), Strasbourg, Montreal, Cologne, and Tianjin, and we anticipate that turnout for the Providence conference will be large and enthusiastic. The overall theme of the conference is intended to foster discussion of how speech production develops, consolidates, and degenerates over the typical lifespan. The meeting is structured around eight invited speakers, each highlighting a subtopic of interest within their session: Developmental • Lisa Goffman (UT Dallas); language acquisition and its disorders Elder speech • Cécile Fougeron (U. Sorbonne); effects of aging on coarticulation Disordered Speech • Suzanne Boyce (U. Cincinnati); articulatory characteristics of motor deficits Modeling • Gabriel Mindlin (U. Buenos Aires); syllabic structure of birdsong Methods • Brad Sutton (U. Illinois); rtMRI as a tool for viewing articulation across the entire vocal tract Neuroscience • Kristofer Bouchard (UCSF); eCOG as an emerging method for investigating speech motor planning and execution Speech Interaction • Jennifer Pardo (Montclair State); aspects of phonetic convergence and turn-taking in conversational dyads Speech Technology • Carol Espy-Wilson (U. Maryland); estimating articulatory gestures from acoustics
For additional details please visit the conference website: https://issp2020.yale.edu
| |||||||
| 3-3-11 | (2020-06-08) *Appel Démos JEP-TALN'20 (JEP-TALN-RECITAL 2020)*, Nancy France *2ième Appel Démos JEP-TALN'20 (JEP-TALN-RECITAL 2020)*
| |||||||
| 3-3-12 | (2020-06-08) *Appel JEP-TALN?20 (JEP-TALN-RECITAL 2020)* Session Doctorants, Nancy France *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 :
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
| |||||||
| 3-3-13 | (2020-06-08) *Appel Tutoriels JEP-TALN'20 (JEP-TALN-RECITAL 2020)*, Nancy France *Appel Tutoriels JEP-TALN'20 (JEP-TALN-RECITAL 2020)*
| |||||||
| 3-3-14 | (2020-06-08) Appel à ateliers Conférence JEP 2020 | TALN 2020 | RECITAL 2020, Nancy, France *Appel à ateliers (JEP-TALN-RECITAL 2020)*
| |||||||
| 3-3-15 | (2020-06-08) Appel à contributions JEP-TALN-RECITAL 2020, Nancy France (UPDATED)
Chers auteurs, chers relecteurs, chers collègues, chers membres de nos communautés,
Face à la situation inédite due à la crise du covid-19, qui annule pour nous toute visibilité sur les mois à venir, il est désormais certain que nous ne pourrons pas maintenir la conférence JEP-TALN-RECITAL 2020 telle que nous l'avions prévue.
En conséquence, nous nous donnons au plus un mois pour décider si la conférence peut avoir lieu sous une autre forme, qui pourrait être une virtualisation totale, un micro-événement avec participation des laboratoires locaux et des autres personnes voulant nous rejoindre et éventuellement des solutions de télé-présence (si les conditions sanitaires l'autorisent sans aucun risque). Nous sommes à l'écoute des suggestions de la communauté et suivons les solutions choisies par les organisateurs d'autres conférences de par le monde (comme ICLR, ICCAPS, ACL, etc.).
En revanche, il est bien évident que cela ne remet pas en cause la publication des actes. *Les actes seront donc publiés*, et nous remercions chaleureusement les auteurs pour leur travail, ainsi que les relecteurs et les membres des comités de programme dont le travail est encore en cours. Nous remercions également les auteurs d'articles RECITAL et de démonstrations qui continuent à soumettre leur recherche. Surtout continuez à nous envoyer vos propositions !
Nous reviendrons donc vers vous dans un mois au plus tard pour préciser l'organisation de l'édition conjointe JEP-TALN-RECITAL 2020.
Vous devinez sans doute notre déception du fait des efforts déjà fournis et de la joie que nous avions à vous accueillir à Nancy en juin. Cette déception concerne aussi tout le personnel support, très présent à nos côtés. Nous en profitons aussi pour remercier nos soutiens institutionnels, académiques et industriels vers lesquels nous reviendrons rapidement. Au-delà, ce qui nous semble important est que nous passions tous ensemble cette crise et qu'elle soit derrière nous le plus rapidement possible.
Si jamais, pour la suite des événements, vous avez des conseils et remarques, nous les attendons volontiers.
Prenez soin de vous, et encore merci pour tous les efforts fournis.
Bien cordialement,
Les organisateurs de JEP-TALN-RECITAL 2020 *JEP'20 call for papers (JEP-TALN-RECITAL 2020)*
| |||||||
| 3-3-16 | (2020-06-15) CfP Workshop on Laughter and Non-Verbal Vocalisations, Bielefeld, Germany (UPDATED) Important dates Submission opens: 14 January 2020 Submission deadline: Acceptance notification: 31 March 2020 Final paper submission: 30 April 2020 Workshop registration deadline: Workshop: Call for Papers, Workshop on Laughter and Non-Verbal Vocalisations, Bielefeld, 15-16 June the previous meetings held in Dublin (2012), Enschede
| |||||||
| 3-3-17 | (2020-06-22) Second ETeRNAL (Ethics and Natural Language Processing) workshop, Nancy, France (UPDATED)
Covid 19: Same status as JEP-TALN
| |||||||
| 3-3-18 | (2020-06-25)Journée de travail du GT2 Intermodalité, multimodalité du GDR TAL - Marseille, France Journée de travail du GT2 Intermodalité, multimodalité du GDR TAL - jeudi 25 juin 2020, Marseille
Le langage naturel est multimodal par essence, alors que la communauté TAL s?est, jusqu?à présent, principalement concentrée sur le message verbal véhiculé, écrit ou oral. Le Groupe de Travail GT2 Intermodalité, multimodalité du GDR TAL (https://gdr-tal.ls2n.fr/) s'intéresse à l'exploration des questions liées à la multimodalité dans le langage : qu'est-ce que le langage multimodal ? Quel est le lien entre multimodalité et communication ? Comment prendre en compte la multimodalité dans les systèmes ? Des applications sont attendues dans les domaines et thématiques de l'accessibilité, de la robotique, des agents de dialogue, et dans bien d'autres champs applicatifs.
Dans ce cadre, le GT2 organise.une journée scientifique qui se déroulera le jeudi 25 juin 2020 à Marseille. Programme de la journée
L?objectif de la session posters est de permettre aux doctorants en TAL mono- ou multimodal intéressés par les problématiques du GT2 de présenter leurs travaux, mêmes préliminaires, afin de se connaître d?une part et de se faire connaître de la communauté TAL multimodal en cours de constitution d?autre part. Tout doctorant désirant participer à cette session transmettra aux organisateurs un titre et un résumé de 15 lignes maximum avant le 15 mai 2020. Le GT2 pourra proposer quelques bourses d'un montant de 200 euros maximum pour aider au financement du déplacement de certains doctorants présentant un poster. La sélection se fondera entre autres sur le nombre de doctorants d?un même laboratoire assistant à la journée, l?année de thèse du doctorant, la distance du voyage... Tout doctorant présentant un poster et intéressé par ce mécanisme adressera, après s?être inscrit via le framaforms (cf. ci-dessous), en plus du titre et du résumé de 15 lignes maximum du poster, un CV court et une lettre de motivation aux organisateurs.
La participation à la journée est gratuite mais pour des questions de logistique, nous nous remercions de vous inscrire dès à présent sur https://framaforms.org/pre-inscription-journee-gdr-tal-gt2-1583242801, et en tous cas avant le 30 avril 2020. Les organisateurs, Benoît Favre (benoit.favre@lis-lab.fr), Damien Lolive (damien.lolive@irisa.fr),
Pascale Sébillot (pascale.sebillot@irisa.fr)
| |||||||
| 3-3-19 | (2020-06-29) ACM Multimedia 2020 Call for Multimedia Grand Challenge Proposals ACM Multimedia 2020 Call for Multimedia Grand Challenge Proposals
ACM Multimedia is the premier international conference in the area of multimedia within the field of computer science. Multimedia research focuses on integration of the multiple perspectives offered by different digital modalities including images, text, video, music, sensor data, spoken audio.
ACM Multimedia is calling for proposals for Grand Challenges in 2020. Proposers with an innovative idea of a Multimedia Grand Challenge, should gather an organizational team with the capacity to carry out the organization of a challenge, and submit a proposal according to the instructions below. In 2020, we are emphasizing the continuity of Grand Challenges, which is important in order to support sustained and substantial progress in the state of the art. We ask that organizer teams who would like to propose Grand Challenges to express a commitment to organize their Grand Challenge multiple years in a row.
The Multimedia Grand Challenge was first presented as part of ACM Multimedia 2009 and has established itself as a prestigious competition in the multimedia community. The purpose of the Multimedia Grand Challenge is to engage the multimedia research community by establishing well-defined and objectively judged challenge problems intended to exercise the state-of-the-art methods and inspire future research directions. The key criteria for Grand Challenges are that they should be useful, interesting, and their solution should involve a series of research tasks over a long period of time, with pointers towards longer-term research.
A Multimedia Grand Challenge proposal should include:
Important Dates
Contacts
For questions regarding the Grand Challenges you can email the Multimedia Grand Challenge Chairs at leizhang@microsoft.com
| |||||||
| 3-3-20 | (2020-06-29) L?école d?été en Traitement automatique des langues (ETAL), Lannion, France (UPDATED) Cancelled sdue to COVID 19. Will probably be postponed to a later date. ETAL 2020
| |||||||
| 3-3-21 | (2020-07-06) 3rd conference on Second Language Acquisition (RéAL2), Toulouse, France 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.
| |||||||
| 3-3-22 | (2020-07-09) ACL 2020 Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML) , Seattle, WA, USA (UPDATED) Covid19
1) As ACL 2020 will be online, the Challenge-HML will also happen online via zoom. Link to the zoom will be announced soon after final discussions with the ACL workshop chairs.
2) All the deadlines on the website are pushed by 20 days to allow those interested in submitting extra time to prepare their papers.
ACL 2020 Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML) Website: http://multicomp.cs.cmu.edu/acl2020multimodalworkshop/ Keynotes:
Important Dates
**All deadlines @11:59 pm anywhere on Earth- year 2020)** Supported by:
================================================================= 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.
We accept the following types of submissions:
Submission must be formatted according to ACL 2020 style files: https://acl2020.org/calls/papers/#paper-submission-and-templates Workshop Organizers
| |||||||
| 3-3-23 | (2020-07-11) CfP FinSBD-2, the 2nd shared task on Sentence Boundary Detection in PDF Noisy Text in the Financial Domain, Yokohama, Japan We would like to invite you to submit to FinSBD-2, the 2nd shared task Register here: https://forms.gle/NixDGuVjrdFMjYhR9 [4]
Collocated with FIN-NLP 2020 workshop: http://finnlp.nlpfin.com [1] Submission deadline: May 8, 2020 Workshop date: IJCAI-PRICAI 2020 @ July 11-13th, 2020, Yokohama, Japan Motivation ======== Sentences Sentences are basic units of the written language. Detecting the beginning and end of sentences, or sentence boundary detection (SBD), is the foundational first step in many Natural Language Processing (NLP) applications such as POS tagging; syntactic, semantic, and discourse parsing; information extraction; or machine translation. Despite its important role in NLP, Sentence Boundary Detection has so far not received enough attention. Especially for noisy texts extracted from machine-readable files (generally PDF file format) such as financial documents. They also contain many visual demarcations indicating a hierarchy of sections including bullets and numbering. There are many sentence fragments and titles, and not just complete sentences. The prospectuses more often than not contain punctuation errors. And in order to structure the dense information in a more easily read format, lists are often used. Lists This year, we have included the task of extracting lists due to their unique structure and common occurrence in financial documents. A list can be similar to a sentence that enumerates several items of the same category. For example, the ?Simple List? from Figure 1 [6] can be easily read as one normal sentence. However, looking at Figure 2 [6], the list cannot be read as one sentence; although it is one unit, because there are multiple sentences included and there is a visible hierarchy of information. It is therefore important to make the distinction between sentences and lists and, for these lists, to create a hierarchy that organizes the items. Mastering this distinction and item hierarchy can pave the way for more accurate information extraction.
Task Description ============= Last year we organized the first edition of FinSBD focusing on extracting well-segmented sentences from Financial prospectuses in PDF format by detecting their beginning and ending boundaries in two languages: English and French. In addition to an improved version of the previously proposed task, this year we are extending this task to include the detection of lists and list items, as well as their hierarchy. FinSBD'2 is split into two sub-tasks: - Extracting sentence boundaries, including list and list item boundaries. - Organizing the lists items hierarchically. For each given PDF, a JSON will be provided containing: - text extracted (key 'text') - sentence boundaries (key 'sentence') - list boundaries (key 'list') - list item boundaries (key 'item') - list item boundaries of level 1 (key 'item1') - list item boundaries of level 2 (key 'item2') - list item boundaries of level 3 (key 'item3') - list item boundaries of level 4 (key 'item4') Item boundaries overlap with item boundaries of different levels. Each item level represents its depth within the list. Boundaries are represented by indexes of starting and ending characters that the system has to predict. We also included the PDF coordinates of each boundaries as metadata (which can be used for visualization on PDF if needed). Example =======
{ 'text': 'Ce document fournit des informations aux investisseurs ...', 'sentence': [{'start': 17, 'end': 53, 'coordinates':...}, ...], 'list': [{'start': 1080, 'end': 1267, 'coordinates':...}, ...], 'item': [...], 'item1': [...], 'item2': [...], 'item3': [...], 'item4': [...] } Sub-task 1 consists in predicting boundaries of sentences, lists and list items. Sub-task 2 consists in predicting boundaries of item1, item2, item3 and item4. We can also see sub-task 2 as refining item boundaries into 4 classes of boundaries (item = item1 + item2 + item3 + item4). Last year, participants were only given indexes of tokens. This year, we are providing indexes of characters as well as coordinates of boundaries to allow different kind of character or word tokenization and/or possible usage of spatial and visual cues. Therefore, we hope to encourage novel approaches based on multimodality, especially since lists are often spatially structured to convey information visually. Improved annotation guidelines will also be provided to explain how the new and richer dataset was created. Participants can choose to work on both languages, or submit systems for one language only. They can participate in one or both sub-tasks. This task is open to everyone. The only exception are the co-chairs of the organizing team, who cannot submit a system, and who will serve as an authority to resolve any disputes concerning ethical issues or completeness of system descriptions. Evaluation ======== For each sub-task, the evaluation metrics will be computed based on boundaries which are pairs of character indexes ('start' and 'end'). The F-score will be the official metric and an evaluation script will be provided to all the teams. Prize ==== A USD$1000 prize will be rewarded to the best-performing teams. Important dates ============ First announcement of the shared task and beginning of registration: 13 March Release of training data and scoring script: before 30 March Test set made available: 1 May
Registration deadline: 8 May Systems' outputs collected: 8 May Shared task system paper submissions due: 15 May Notification of acceptance: 31 May Camera-ready version of shared task system papers due: 15 June FinNLP 2020 Workshop: 11-13 July Contact ====== For any questions on the shared task please contact us on fin.sbd.task@gmail.com [5] Shared Task Organizing committee =========================== Abderrahim AIT-AZZI, Fortia Financial Solutions Willy AU, Fortia Financial Solutions Bianca CHONG, Fortia Financial Solutions Dialekti VALSAMOU-STANISLAWSKI, Fortia Financial Solutions Sincerely, The FinSBD Organizers IJCAI-20 Read more: https://sites.google.com/nlg.csie.ntu.edu.tw/finnlp2020/shared-task-finsbd-2 [1] FinNLP: http://finnlp.nlpfin.com [2] FinSBD-2: https://sites.google.com/nlg.csie.ntu.edu.tw/finnlp2020/shared-task-finsbd-2 [3] IJCAI-20: https://ijcai20.org/ [4] Registration form: https://forms.gle/NixDGuVjrdFMjYhR9 [5] mailto: fin.sbd.task@gmail.com
| |||||||
| 3-3-24 | (2020-07-11) ROBOTDIAL Workshop 2020, Yokohama, Japan (UPDATED) ROBOTDIAL Workshop 2020 COVID 19 update: IJCAI-PRICAI-2020 will take place in some form, and papers accepted to IJCAI-PRICAI will be published in the proceedings.
| |||||||
| 3-3-25 | (2020-07-15)CfP SIG:Prosodic and phonetic features of speaking styles, Aix en Provence, France (UPDATED)
IMP0RTANT UPDATE
Due to Coronavirus, we have sadly had to postpone the conference until 2021. We will be updating this page as more information becomes available
In the meantime, keep safe and we hope to see you in Aix in 2021!
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 Coordinator of the SIG: Sophie Herment, Aix Marseille Univ, Laboratoire Parole et Langage
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
| |||||||
| 3-3-26 | (2020-07-20) International Conference on Signal Processing and Communications (SPCOM), Bangalore, India (UPDATED) Covid19: Decision will be taken by early May 2020 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
| |||||||
| 3-3-27 | (2020-07-27) 4th INTERNATIONAL SUMMER SCHOOL ON DEEP LEARNING, Leon, Guanajuato, Mexico (UPDATED) Due to Covid-19, DeepLearn 2020 is rescheduled to be held on January 11-15, 2021 in Bilbao, Spain 4th INTERNATIONAL SUMMER SCHOOL ON DEEP LEARNING
| |||||||
| 3-3-28 | (2020-08-09) AILA 2020 CONGRESS: EVALUATING MULTIMODAL DOCUMENTS, Groningen, The Netherlands EVALUATING MULTIMODAL DOCUMENTS At the AILA 2020 CONGRESS
09-14 August 2020 ? Groningen ? The Netherlands
See below for details.
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 .
Symposium Organisers:
Ielka van der Sluis 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
| |||||||
| 3-3-29 | (2020-08-13) Nordic prosody conference, Sonderborg,Denmark (UPDATED) 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: ************** 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.
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.
| |||||||
| 3-3-30 | (2020-08-24) The 28th European Signal Processing Conference (EUSIPCO 2020), Amsterdam , The Netherlands, UPDATED UPDATE COVID 19 The conference is postponed to January 18-22 2021. See http://2020.eusipco.org The 28th European Signal Processing Conference (EUSIPCO 2020)
| |||||||
| 3-3-31 | (2020-08=31) 1st Call for paper – RO-MAN 2020 Special Session in Dialogue Management Systems for Human-Robot Interaction , Naples, Italy 1st 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 31st to September 4th. 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):
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
| |||||||
| 3-3-32 | (2020-09-07) CfP Text Mining and Applications (TEMA2020) , Lisboa, Portugal Call for Papers ? Text Mining and Applications (TEMA?20) Track of EPIA?20
| |||||||
| 3-3-33 | (2020-09-08 )TSD 2020 - PRELIMINARY ANNOUNCEMENT and CALL for WORKSHOPS, Brno, Czech Republic ************************************************************
| |||||||
| 3-3-34 | (2020-09-08) TSD 2020 - SECOND CALL FOR PAPERS, Brno, Czech Republic (UPDATED) *********************************************************
| |||||||
| 3-3-35 | (2020-09-13) CfP Workshop Cognitive Aspects of the Lexicon (CogALex), Barcelona, Spain Call for Papers
CogALex Cognitive Aspects of the Lexicon
Workshop co-located with COLING Paper submission deadline: May 14, 2020
deadline for shared-task papers : May 20, 2020 For latest information always look here https://sites.google.com/view/cogalex-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 ? Search based on sound (rhymes), meaning or contextually related words (associations);
The workshop features two tracks:
The regular research track submissions should follow one of the 2 formats:
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
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
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)
| |||||||
| 3-3-36 | (2020-09-13) FinTOC?2 shared task at COLING2020, Barcelona, Spain UPDATED
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
| |||||||
| 3-3-37 | (2020-09-15) ADReSS challenge, Shanghai, China (UPDATED) Due to the COVID19, INTERSPEECH 2020 has new dates: 26-29 October 2020 Call for Participation: -----------------------
Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challenge at INTERSPEECH 2020 (Sep 15-18, Shanghai, China) Dementia is a category of neurodegenerative diseases that entails a long-term and usually gradual decrease of cognitive functioning. While a number of studies have investigated speech and language features for the detection of Alzheimer's Disease and mild cognitive impairment, and proposed various signal processing and machine learning methods for this prediction task, the field still lacks balanced and standardised data sets on which these different approaches can be systematically compared. The ADReSS Challenge has made available a benchmark dataset of spontaneous speech, which is acoustically pre-processed and balanced in terms of age and gender, defining a shared task through which different approaches to AD recognition in spontaneous speech can be compared. We invite researchers working on speech and language analysis methods for detection of AD and/or assessment of cognitive status to develop or test their approaches to these tasks on the ADReSS Challenge dataset, and to submit a paper for presentation at INTERSPEECH'2020, in the Challenge's special session. The relevant dates are: * January 24, 2020: ADReSS training data available * March 15, 2020: ADReSS test data made available * March 17, 2020: Period for submission of results opens * March 30, 2020: *INTERSPEECH'2020 paper submission deadline* * June 19, 2020: Paper acceptance/rejection notification * September 15-18, 2020: INTERSPEECH'2020, in Shanghai, China. For further details please see https://edin.ac/375QRNI Organizers - Saturnino Luz, Usher Institute, The University of Edinburgh - Fasih Haider, The University of Edinburgh - Sofia de la Fuente, The University of Edinburgh - Davida Fromm, Carnegie Mellon University - Brian MacWhinney, Carnegie Mellon University
| |||||||
| 3-3-38 | (2020-09-21)CfP MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP 2020), Espoo ,Finland MLSP 2020 https://ieeemlsp.cchttps://ieeemlsp.cc https://ieeemlsp.cc Call for PapersMachine 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:
Special Session Call for ProposalsMLSP 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. Paper SubmissionProspective authors are invited to submit a double column paper of up to six pages using the electronic submission procedure which will be peer-reviewed. Paper PublicationAccepted 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
Organizing CommitteeGeneral 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)
| |||||||
| 3-3-39 | (2020-09-22) ImageCLEF 2020 ImageCLEF 2020 Thessaloniki, Greece ImageCLEF 2020
| |||||||
| 3-3-40 | (2020-10-06) SPECOM 2020, St Petersburg, Russia ********************************************************* 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 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 SPECOM Proceedings will be published by Springer as a book in the Lecture Notes in Artificial Intelligence (LNAI/LNCS) series listed in all major international citation databases. SPECOM Proceedings are included in the list of forthcoming proceedings for October 2020.
IMPORTANT DATES May 26, 2020 ............ Submission of full papers July 03, 2020 ............ Notification of acceptance July 17, 2020 ............ Camera-ready papers and early registration October 06-10, 2020 ......... Conference dates
CONTACTS All correspondence regarding the conference should be addressed to: SPECOM-2020 Secretariat: E-mails: specom@iias.spb.su SPECOM-2020 web-site: www.specom.nw.ru/2020
| |||||||
| 3-3-41 | (2020-10-12) 3rd International Workshop on Multimedia Content Analysis in Sports (MMSports'20), Seattle, USA Call for Papers ------------------- Third International Workshop on Multimedia Content Analysis in Sports (MMSports'20) @ ACM Multimedia, October 12-16, 2020, Seattle, USA
We'd like to invite you to submit your paper proposals for the 3rd International Workshop on Multimedia Content Analysis in Sports to be held in Seattle, USA together with ACM Multimedia 2020. The ambition of this workshop is to bring together researchers and practitioners from different disciplines to share ideas on current multimedia/multimodal content analysis research in sports. We welcome multimodal-based research contributions as well as best-practice contributions focusing on the following (and similar, but not limited to) topics:
– annotation and indexing – athlete and object tracking – activity recognition, classification and evaluation – event detection and indexing – performance assessment – injury analysis and prevention – data driven analysis in sports – graphical augmentation and visualization in sports – automated training assistance – camera pose and motion tracking – brave new ideas / extraordinary multimodal solutions
Submissions can be of varying length from 4 to 8 pages, plus additional pages for the reference pages. There is no distinction between long and short papers, but the authors may themselves decide on the appropriate length of the paper.
Please refer to the workshop website for further information: http://mmsports.multimedia-computing.de
IMPORTANT DATES Submission Due: June 29, 2020 Acceptance Notification: July 31, 2020 Camera Ready Submission: August 7, 2020 Workshop Date: TBA; either Oct 12 or Oct 16, 2020
| |||||||
| 3-3-42 | (2020-10-12) ACM Multimedia, Seattle, WA, USA ===== ACM Multimedia 2020 =====
| |||||||
| 3-3-43 | (2020-10-14) 8th INTERNATIONAL CONFERENCE ON STATISTICAL LANGUAGE AND SPEECH PROCESSING, Cardiff, United Kingdom
| |||||||
| 3-3-44 | (2020-10-25) CfW International Conference on Multimodal Interaction ( ICMI 2020), Utrecht, The Netherlands (UPDATED) COVID-19 announcement Dear all,
We hope you are healthy in these worrying times. We are closely monitoring the COVID-19 situation in the Netherlands and around the world. There are many uncertainties, but we will try to give you more information about the format of the conference as soon as possible. What we do know for certain, is that we will publish ICMI2020 proceedings this year.
Also note that we have extended the submission deadline for Long and Short papers to 29 May 2020.
https://icmi.acm.org/2020/index.php?id=CfW ***********************************************************************************
The International Conference on Multimodal Interaction (ICMI 2020) will be held in Utrecht, the Netherlands, October 25-29, 2020. ICMI is the premier international conference for multidisciplinary research on multimodal human-human and human-computer interaction analysis, interface design, and system development. The theme of the ICMI 2020 conference is Art, Culture, and Society. ICMI has developed a tradition of hosting workshops in conjunction with the main conference to foster discourse on new research, technologies, social science models and applications. Examples of recent workshops include:
- Media Analytics for Societal Trends - Neuromanagement and Intelligent Computing - Multi-sensorial Approaches to Human-Food Interaction - Group Interaction Frontiers in Technology - Modeling Cognitive Processes from Multimodal Data - Human-Habitat for Health - Multimodal Analyses enabling Artificial Agents in Human-Machine Interaction - Investigating Social Interactions with Artificial Agents - Child Computer Interaction - Multimodal Interaction for Education
We are seeking workshop proposals on emerging research areas related to the main conference topics, and those that focus on multi-disciplinary research. We would also strongly encourage workshops that will include a diverse set of keynote speakers (factors to consider include: gender, ethnic background, institutions, years of experience, geography, etc.).
The content of accepted workshops are under the control of the workshop organizers. Workshops may be of a half-day or one day in duration. Workshop organizers will be expected to manage the workshop content, solicit submissions, be present to moderate the discussion and panels, invite experts in the domain, conduct the reviewing process, and maintain a website for the workshop. Workshop papers will be indexed by ACM Digital Library in an adjunct proceedings, and a short workshop summary by the organizers will be published in the main conference proceedings.
Submission
Prospective workshop organizers are invited to submit proposals in PDF format (Max. 3 pages). Please email proposals to the workshop chairs: Yukiko Nakano (y.nakano@st.seikei.ac.jp) and Albert Ali Salah (a.a.salah@uu.nl) The proposal should include the following:
- Workshop title - List of organizers including affiliation, email address, and short biographies - Workshop motivation, expected outcomes and impact - Tentative list of keynote speakers - Workshop format (by invitation only, call for papers, etc.), anticipated number of talks/posters, workshop duration (half-day or full-day) including tentative program - Planned advertisement means, website hosting, and estimated participation - Paper review procedure (single/double-blind, internal/external, solicited/invited-only, pool of reviewers, etc.) - Paper submission and acceptance deadlines - Special space and equipment requests, if any
Important Dates: Workshop proposal submission: Monday, February 10, 2020 Notification of acceptance: Monday, February 24, 2020 Workshop papers due: End of July, 2020 (suggested) Workshop dates: October 25 or 29, 2020
| |||||||
| 3-3-45 | (2020-10-25) ICMI 2020: Call for Multimodal Grand Challenges Call for Multimodal Grand Challenges *************************************** ICMI 2020: Call for Multimodal Grand Challenges https://icmi.acm.org/2020/index.php?id=CfC 25-29 Oct 2020, Utrecht, The Netherlands ***************************************
We are calling for teams to propose one or more ICMI Multimodal Grand Challenges.
The International Conference on Multimodal Interaction (ICMI) is the premier international forum for multidisciplinary research on multimodal human-human and human-computer interaction, interfaces, and system development. Developing systems that can robustly understand human-human communication or respond to human input requires identifying the best algorithms and their failure modes. In fields such as computer vision, speech recognition, computational (para-) linguistics and physiological signal processing, for example, the availability of datasets and common tasks have led to great progress. We invite the ICMI community to collectively define and tackle the scientific Grand Challenges in our domain for the next 5 years. ICMI Multimodal Grand Challenges aim to inspire new ideas in the ICMI community and create momentum for future collaborative work. Analysis, synthesis, and interactive tasks are all possible.
Challenge papers will be indexed in the main proceedings of ICMI.
The grand challenge sessions are still to be confirmed. We invite organizers from various fields related to multimodal interaction to propose and run Grand Challenge events. We are looking for exciting and stimulating challenges including but not limited to the following categories:
- Dataset-driven challenge: This challenge will provide a dataset that is exemplary of the complexities of current and future multimodal problems, and one or more multimodal tasks whose performance can be objectively measured and compared in rigorous conditions. Participants in the Challenge will evaluate their methods against the challenge data in order to identify areas of strengths and weaknesses. - Use-case challenge: This challenge will provide an interactive problem system (e.g. dialog-based or non-verbal-based) and the associated resources, which can allow people to participate through the integration of specific modules or alternative full systems. Proposers should also establish systematic evaluation procedures. - Health challenge: This challenge will provide a dataset that is exemplary of a health related task, whose analysis, diagnosis, treatment or prevention can be aided by Multimodal Interactions. The challenge should focus on exploring the benefits of multimodal (audio, visual, physiological, etc) solutions for the stated task. - Policy challenge: Legal, ethical, and privacy issues of Multimodal Interaction systems in the age of AI. The challenge could revolve around opinion papers, panels, discussions, etc.
Prospective organizers should submit a five-page maximum proposal containing the following information:
1.Title 2.Abstract appropriate for possible Web promotion of the Challenge 3.Distinctive topics to be addressed and specific goals 4.Detailed description of the Challenge and its relevance to multimodal interaction 5.Length (full day or half day) 6.Plan for soliciting participation 7.Description of how submissions (challenge?s submissions and papers) will be evaluated, and a list of proposed reviewers 8.Proposed schedule for releasing datasets (if applicable) and/or systems (if applicable) and receiving submissions 9.Short biography of the organizers (preferably from multiple institutions) 10.Funding source (if any) that supports or could support the challenge organization 11.Draft call for papers; affiliations and email address of the organisers; summary of the Grand Challenge; list of potential Technical Program Committee members and their affiliations, important dates
Proposals will be evaluated based on originality, ambition, feasibility, and implementation plan. A Challenge with dataset(s) or system(s) that has had pilot results to ensure its representativity and suitability to the proposed task will be given preference for acceptance; an additional 1 page description must be attached in such case. Continuation of or variants on the 2019 challenges are welcome, though we ask for submissions of this form to highlight the number of participants that attended during the previous year and describe what changes (if any) will be made from the previous year.
The ICMI organizers will offer support with basic logistics, which includes rooms and equipment to run the Workshop, coffee breaks can be offered if synchronised with the main conference.
Important Dates and Contact Details
Proposals due: January 13, 2020 Proposal notification: February 3, 2020 Paper camera-ready: August 17, 2020
Proposals should be emailed to both ICMI 2020 Multimodal Grand Challenge Chairs, Dr. Hayley Hung and Dr. Laura Cabrera-Quiros via grandchallenge.ICMI20@gmail.com. Prospective organizers are also encouraged to contact the co-chairs if they have any questions. Proposals are due by January 13, 2020. Notifications will be sent on February 3, 2020.
| |||||||
| 3-3-46 | (2020-10-25) ICMI 2020: First Call for Demonstrations and Exhibits, Utrecht, The Netherlands ICMI 2020: First Call for Demonstrations and Exhibits ******************************************************* We invite you to submit your proposals for demonstrations and exhibits to be held during the 22nd ACM International Conference on Multimodal Interaction (ICMI 2020), located in Utrecht, the Netherlands, October 25-29th, 2020. This year?s conference theme: In this information age, technological innovation is at the core of our lives and rapidly transforming and impacting the state of the world in art, culture, and society, and science as well - the borders between classical disciplines such as humanities and computer science are fading. In particular, we wonder how multimodal processing of human behavioural data can create meaningful impact in art, culture, and society practices. And vice versa, how does art, culture, and society influence our approaches and techniques in multimodal processing? As such, this year, ICMI welcomes contributions on our theme for Multimodal processing and representation of Human Behaviour in Art, Culture, and Society. Demonstrations and Exhibits The ICMI 2020 Demonstrations & Exhibits session is intended to provide a forum to showcase innovative implementations, systems and technologies demonstrating new ideas about interactive multimodal interfaces. It can also serve to introduce commercial products. Proposals may be of two types: demonstrations or exhibits. The main difference is that demonstrations include a 1-2 page paper, which will be included in the ICMI main proceedings, while the exhibits only need to include a brief outline (no more than one page; not included in ICMI proceedings). We encourage both the submission of early research prototypes and interesting mature systems. In addition, authors of accepted regular research papers may be invited to participate in the demonstration sessions as well. Demonstration Submission Please submit a 1-2 page description of the demonstration through the main ICMI conference management system (https://new.precisionconference.com/sigchi). Demonstration description(s) must be in PDF format, according to the ACM conference format, of no more than 2 pages in length including references (submission format: http://icmi.acm.org/2020/index.php?id=authors). Demonstration proposals should include a description with photographs and/or screen captures of the demonstration and, where possible, a video of the proposed demo should accompany the submission (no larger than 200MB). The demo and exhibit paper submissions are not anonymous. However, all ACM rules and guidelines related to paper submission should be followed (e.g. plagiarism, including self-plagiarism). The demonstration submissions will be peer reviewed, according to the following criteria: suitability as a demo, scientific or engineering feasibility of the proposed demo system, application, or interactivity, alignment with the conference focus, potential to engage the audience, and overall quality and presentation of the written proposal. Authors are encouraged to address such criteria in their proposals (paper submission), along with preparing the short papers mindful of the quality and rigorous scientific expectations of an ACM publication. The demo program will include the accepted proposals and may additionally include invited demos from among full-length papers accepted for presentation at the conference. Please note that the accepted descriptions will be included in the ICMI main proceedings. Exhibit Submission Exhibit proposals should be submitted following the same guidelines, formatting, and due dates as for demonstration proposals. Exhibit proposals must be shorter in length (up to one page) and more suitable for mature systems. Exhibits will not have a paper published in the ICMI 2020 proceedings. Attendance At least one author of all accepted Demonstrations and Exhibits submissions must register for and attend the conference, including the conference demonstrations and exhibits session(s). Important Dates Submission of demo and exhibit proposals July 17, 2020 Demo and exhibit notification of acceptance July 31, 2020 Submission of demo final papers August 17, 2020 Questions? For further questions, contact the Demonstrations and Exhibits co-chairs: Zakia Hammal (Zakia_Hammal@yahoo.fr) and Dominique Vaufreydaz (Dominique@research.vaufreydaz.org)
| |||||||
| 3-3-47 | (2020-10-?) The VoicePrivacy2020 Challenge Evaluation Plan The VoicePrivacy 2020 Challenge Evaluation Plan is available on the website: https://www.voiceprivacychallenge.org/docs/VoicePrivacy_2020_Eval_Plan_v1_1.pdfThe VoicePrivacy initiative Challenge is spearheading the effort to develop privacy preservation solutions for speech technology. It aims to gather a new community to define the task and metrics and to benchmark initial solutions using common datasets, protocols and metrics. VoicePrivacy takes the form of a competitive challenge. The challenge is to develop anonymization solutions which suppress personally identifiable information contained within speech signals. At the same time, solutions should preserve linguistic content and speech quality/naturalness. The challenge will conclude with a session/event held in conjunction with Interspeech 2020 at which challenge results will be made publicly available. Please find more information about on the challenge website: http://www.voiceprivacychallenge.org
Registration: Participants/teams are requested to register for the evaluation. Registration should be performed once only for each participating entity and by sending an email to: organisers@lists.voiceprivacychallenge.org Subscription: Participants are encouraged to subscribe to the VoicePrivacy 2020 mailing list by sending an email to: sympa@lists.voiceprivacychallenge.org with ?subscribe 2020? as the subject line. Successful registrations are confirmed by return email. To post messages to the mailing list itself, emails should be addressed to: 2020@lists.voiceprivacychallenge.org
Jean-François Bonastre - University of Avignon - LIA, France
| |||||||
| 3-3-48 | (2021-01-17) Advanced Language Processing School (ALPS) , Grenoble, France FIRST CALL FOR PARTICIPATION
?
Advanced Language Processing School (ALPS) Jan, 17-22 2021 Grenoble - France ? University Grenoble Alpes and Naver Labs Europe are announcing the first Advanced Language Processing School (ALPS) in Grenoble. ? Important Dates Application Deadline - July, 15th 2020 Notification - Sept 15th 2020 Registration Deadline - Oct, 15th 2020 Winter School - Jan, 17-22 2021 ? Target Audience This is a winter school covering advanced topics in NLP, and we are primarily targeting doctoral students and advanced (research) masters. A few slots will also be reserved to academics and persons working in research-heavy positions in industry.
?
Characteristics This winter school aims to provide talks of renowned NLP researchers, as well as creating an ideal environment to work together. Confirmed speakers so far: - Isabelle Augenstein (Copenhagen, DEN) - Tim Baldwin (Melbourne, AUS) - Kyunghyun Cho (NYU and FAIR, USA) - Yejin Choi (University of Washington and Allen Institute for AI, USA) - Grzegorz Chrupa?a (Tilburg University, NED) - Claire Gardent (LORIA, FR) - Sanjeev Khudanpur (JHU, USA) ? In addition of the talks, an important aspect of this school is the interaction between participants. The registration fee will cover full board in a residence close to a ski resort, and some of the afternoons there will be organised social activities. ? Website: http://alps.imag.fr/ Questions: alps2021@univ-grenoble-alpes.fr
| |||||||
| 3-3-49 | (2021-?-?) CfP The Ninth Dialog System Technology Challenge (DSTC9) Call for Participation: The Ninth Dialog System Technology Challenge (DSTC9)
Website: https://sites.google.com/dstc.community/dstc9/home The DSTC shared tasks have provided common testbeds for the dialog research community since 2013. From its sixth edition, it has been rebranded as 'Dialog System Technology Challenge' to cover a wider variety of dialog related problems. For this year's challenge, we opened the call for track proposals and selected the following four parallel tracks by peer-reviews: - Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access (Amazon Alexa AI): This track aims to allow users to have requests that are out of the scope of APIs/DB but potentially available in external knowledge sources. Track participants will develop task-oriented dialogue systems to understand relevant domain knowledge, and generate system responses with the relevant selected knowledge. In addition, the track includes evaluation on generalization over unseen domains and modalities (i.e. moving from written to spoken conversations). - Multi-domain Task-oriented Dialog Challenge II (Microsoft Research AI & Tsinghua University): This track follows its success in DSTC-8 continuing with the effort of building dialog systems under a multi-domain setting. This time extending the task by incorporating new datasets, creating new sub-tasks, and providing a new development platform. The new task specifically focuses on two aspects of dialog systems: language portability and end-to-end system complexity. - Interactive Evaluation of Dialog (CMU & USC): This track targets the creation of systems that can be effectively used in interactive settings by real users. The task is intended to move research beyond datasets, and evaluate models in interactive environments with real users allowing several valuable properties of dialog to be measured: consistency, adaptiveness and user-centric development. DialPort, a platform for interactive assessment with real users will be used for evaluation. - SIMMC: Situated Interactive Multi-Modal Conversational AI (Facebook Assistant & Facebook AI): This track aims to tackle grounding dialog in an evolving multi-modal contextual input. Unlike previous multimodal track challenges, where the context from the non-textual modalities (video and audio) remains unchanged as the dialog progresses, this track encompasses a rich, situated multi-modal user context in the form of a shared image or VR environment that evolves fluidly based on the dialog flow. Participation is welcomed from any research team (academic, corporate, non-profit, government). - Jun 15, 2020: Training data is released - Sep 21, 2020: Test data is released - Oct 5, 2020: Entry submission deadline - Nov 2020: Paper submission deadline - Spring 2021: DSTC9 workshop (venue: TBD) - Chulaka Gunasekara - IBM Research AI, USA - Abhinav Rastogi - Google Research, USA - Yun-Nung (Vivian) Chen - National Taiwan University, Taiwan - Luis Fernando D'Haro - Universidad Politécnica de Madrid, Spain - Seokhwan Kim - Amazon Alexa AI, USA Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access - Seokhwan Kim, Mihail Eric, Behnam Hedayatnia, Karthik Gopalakrishnan, Yang Liu, Dilek Hakkani-tur (Amazon Alexa AI) Multi-domain Task-oriented Dialog Challenge II - Baolin Peng, Jianfeng Gao, Jinchao Li, Lars Liden, Minlie Huang, Qi Zhu, Runze Liang, Ryuichi Takanobu, Shahin Shayandeh, Swadheen Shukla, Zheng Zhang (Microsoft Research AI & Tsinghua University) Interactive Evaluation of Dialog - Shikib Mehri, Carla Gordon, David Traum, Maxine Eskenazi (CMU & USC) SIMMC: Situated Interactive Multi-Modal Conversational AI - Ahmad Beirami, Eunjoon (EJ) Cho, Paul A. Crook, Ankita De, Alborz Geramifard, Satwik Kottur, Seungwhan Moon, Shivani Poddar, Rajen Subba (Facebook Assistant & Facebook AI) - Koichiro Yoshino - Nara Institute of Science and Technology (NAIST), Japan - Chiori Hori - Mitsubishi Electric Research Laboratories (MERL), USA - Rafael E. Banchs - Nanyang Technological University (NTU), Singapore - Michel Galley - Microsoft Research AI, USA Join the DSTC mailing list to get the latest updates about DSTC9: - To join the mailing list: visit https://groups.google.com/a/dstc.community/forum/#!forum/list/join - To post a message: send your message to list@dstc.community - To leave the mailing list: visit https://groups.google.com/a/dstc.community/forum/#!forum/list/unsubscribe For specific enquiries about DSTC9: Please feel free to contact dstc9-organizing-committee@dstc.community.
| |||||||