Dear all,
* Apologies for cross-posting *
Speech interfaces are customary in many types of robots and robotic
applications. Despite the progress in speech recognition and many other
areas of natural language processing in recent years, failures of speech
interfaces in robotic scenarios are numerous and commonplace. In contrast
to the shared experience of failure of speech interfaces in robotics, the
literature is positively skewed towards the success and good performance of
these. The documentation of failure speech interfaces on the other hand is
exceedingly rare and a systematic study of failure and its causes is
non-existent.
The WTF workshop aims at bringing together a multidisciplinary group of
researchers from the fields of robotics, human-Robot Interaction (HRI),
natural language processing, conversation analysis and pragmatics and
industrial partners to address this gap. The workshop aims to provide a
platform to *discuss the multitude of failures of speech interfaces* openly
and, if possible, systematically, in the hope of identifying the most
fruitful *directions for overcoming these failures* in future systems. The
workshop will focus on *human-robot joint action scenarios* involving
*multimodal
coordination* between humans and robots as these are the norm in scenarios
where robotic speech interfaces are deployed.
*Format*:
The workshop will take place in *two parts*, with the *first part being
online*, and the *second part being on site at the University of
Hertfordshire. *The two parts are complementary, and the work of the
on-site part will build on the outcome from the online part.
Both parts will consist of a combination of keynote talks by experts in the
field followed by bash talks and group discussions on the different types
of failures.
*Workshop website*:
https://sites.google.com/view/wtfworkshop2022/
*IMPORTANT: *While the online part was held on the 16th and 17th of June,
we are now reopening the *call for participation for the on site part *of
the 5th of September. Interested participants who did not take part in the
online session are welcome to apply and join us in the discussion!
*Dates:*
-
*Application**: *22nd July 2022 (Notification of Acceptance on the 29th)
-
*Workshop - On-site part: *5th September 2022, full day (9:30am to 5pm)
*Applications for participation should be submitted before or on the **22*
*nd* *of Ju**ly* via the following link:
https://sites.google.com/view/wtfworkshop2022/dates-and-submission
We have limited funding available to cover travel and accomodation costs
for travel within the UK. See the workshop website for details.
*Outcomes*:
Apart from hopefully lively discussions and exchanges about the most
pressing failures in such speech interfaces, the intended outputs of this
workshop are twofold:
-
A position paper summarizing the kinds of failures commonly observed by
researchers working on (or with) robotic speech interfaces, and the most
promising future directions to overcome these,
-
The identification of a prototypical application scenario embodying most
of the identified challenges that may act as a future benchmark.
*Organizers*:
-
Frank Förster, University of Hertfordshire
-
Christian Dondrup, Heriot-Watt University
-
Joel Fischer, University of Nottingham
-
Marta Romeo, University of Manchester
-
Patrick Holthaus, University of Hertfordshire
-
Luke Wood, University of Hertfordshire
*Contact*:
For all inquiries or early expressions of interest, contact Frank Foerster (
f.foerster(a)herts.ac.uk)
GENERAL INFORMATION
The 11th Computational Linguistics Fall School of the Special Interest
Group on Computational Linguistics of the German Linguistic Society
(Deutsche Gesellschaft für Sprachwissenschaft, DGfS) will take place in
Berlin from 19th to 23th of September 2022:
https://dgfs-clschool22.github.io
The event is organized by the Institute for German Language and
Linguistics (IdSL) at the Humboldt University in Berlin and the Leibniz
Center of General Linguistics (ZAS). The DGfs-CL fall school is a
biennial event for students who wish to broaden their knowledge of
techniques and methods used in natural language processing in fields not
traditionally taught in standard degree programs.
COURSE PROGRAM
This year the following two courses, taught in English, will be offered:
- Heriberto Cuayahuitl (Lincoln University): Deep Reinforcement Learning
for Dialogue Generation
- Carina Silberer (Stuttgart University): Visually Grounded Lexical
Semantics
There will also be an evening lecture by Tibor Kiss (Linguistics Data
Science Lab) entitled: From Architect to Nothingness: what happened to
Linguistics in Computational Linguistics?
Additionally, there will be an industry exchange forum.
REGISTRATION
https://dgfs-clschool21.github.io/registration
For more information about participation fees, course details,
scholarship options, venue and accommodation, please visit the website
of the fall school.
Contact: Sophia Höbel (hoebelleibniz-zas.de)
Apologies for cross-posting.
** Short papers SemDial 2022 **
** Submission deadline extended to 22 July 2022 **
---------------------------------------------------------------
SemDial 2022 - DubDial
THE 26TH WORKSHOP ON THE SEMANTICS AND PRAGMATICS OF DIALOGUE
https://semdial2022.github.io/
22-24 August 2022
Dublin // Online
---------------------------------------------------------------------
DubDial will be the 26th edition of the SemDial workshop series, which aims to bring together researchers working on the semantics and pragmatics of dialogue in fields such as formal semantics and pragmatics, computational linguistics, artificial intelligence, philosophy, psychology, and neuroscience.
In 2022 the workshop will be hosted by the Information, Communication and Entertainment Research Institute at Technological University Dublin, Ireland and the SFI ADAPT Research Centre. There will also be an online component for those who cannot travel to Dublin. Please see the website for updates closer to the date.
*WEBSITE:*
https://semdial2022.github.io/
This year, there will be a guiding theme for the conference: Interactivism. The interactivist model (Bickhard, 2009) offers a new dynamic approach to understanding language, communication, and cognition. Across many disciplines, from philosophy to neuroscience and robotics, there is recognition that explanations of life and mind need to be grounded in the physics of far-from-equilibrium, interactive systems. From this starting point, explanations have been developed for phenomena ranging from representation, perception, and action to motivation, memory, learning and development, emotions, consciousness, rationality, sociality, personality and psychopathology. This work has yet to develop interfaces with studies of specific phenomena in dialogue modelling and our purpose is to open the discussion on how dialogue researchers can take advantage of this and related perspectives like Enactivism and Ecological Psychology.
*SCOPE:*
We welcome submissions on this special theme of Interactivism and we continue to welcome any papers with formal, computational and empirical approaches to the semantics and pragmatics of dialogue, including, but not limited to:
- the dynamics of agents' information states in dialogue
- common ground / mutual belief
- goals, intentions and commitments in communication
- turn-taking and interaction control
- semantic/pragmatic interpretation in dialogue
- dialogue and discourse structure
- categorisation of dialogue phenomena in corpora
- child-adult interaction
- psycholinguistics of dialogue
- language learning through dialogue
- gesture, gaze, and intonational meaning in communication
- multimodal and multi-party dialogue
- interpretation and reasoning in spoken dialogue systems
- dialogue management
- designing and evaluating dialogue systems
- modelling miscommunication, disfluency, and repair
- applications of the Interactivist model in dialogue phenomena
- enactive approaches to interaction
- dialogue/interaction studies from an Ecological Psychology perspective
*INVITED SPEAKERS:*
* Mark H. Bickhard
* Yvette Graham
* Joanna Rączaszek-Leonardi
*DEADLINE EXTENSION for short-paper submissions*
We invite NON-ANONYMOUS SUBMISSIONS for 2-page short papers. The deadline has now been extended to the *22 July 2022*
Authors should submit a paper of at most 2 pages of content (1 additional page is allowed for references). Formatting instructions and the URL of the submission site are available on the DubDial website:
https://semdial2022.github.io/?page=call#
Short-paper submissions will not be refereed but evaluated for relevance only by the chairs. As such, papers do not need to be anonymised. They will be presented as posters at the workshop.
*IMPORTANT DATES:*
Short paper submissions due: 22 July 2022
Notification: 25 July 2022
Camera-ready submissions deadline: 8th August 2022
*REGISTRATION*
Registration is now open:
https://semdial2022.github.io/?page=registration#
DubDial - SemDial 2022<https://semdial2022.github.io/?page=registration#>
SemDial 2022 (LondonLogue) - The 26th Workshop on the Semantics and Pragmatics of Dialogue. TUD, August 22-24th, 2022
semdial2022.github.io
*RELATED EVENTS*
The final session of SemDial will be the second edition of SummDial, a special session on Summarization of Dialogues and Multi-Party Meetings, for which there is a separate submission process - please see the SummDial website:
https://elitr.github.io/automatic-minuting/summdial-2022.html
*TECHNICAL PROGRAMME CHAIRS:*
Eleni Gregoromichelaki (University of Gothenburg)
Julian Hough (Queen Mary University of London)
John Kelleher (Technological University Dublin)
Contact: pcchairs.semdial2022(a)gmail.com
*LOCAL ORGANISATION:*
John Kelleher, the Information, Communication and Entertainment Research Institute at Technological University Dublin, Ireland and the SFI ADAPT Research Centre.
Contact: organisers.semdial2022(a)gmail.com
*PROGRAMME COMMITTEE:*
Jedediah Allen, Maxime Amblard, Ron Artstein, Alex Berman, Mark Bickhard, Maria Boritchev, Ellen Breitholtz, Harry Bunt, Heather Burnett, Robin Cooper, Valeria de Paiva, Emilie Destruel, Simon Dobnik, Kerstin Fischer, Kallirroi Georgila, Emer Gilmartin, Jonathan Ginzburg, Christine Howes, Julie Hunter, Nikolai Ilinykh, Ruth Kempson, Staffan Larsson, Alex Lascarides, Andy Lücking, Chiara Mazzocconi, Gregory Mills, Robert Mirski, Bill Noble, Massimo Poesio, Laurent Prévot, Matthew Purver, Joanna Raczaszek-Leonardi, Hannes Rieser, Robert Ross, Mehrnoosh Sadrzadeh, David Schlangen, Matthew Stone, Peter Sutton, Lucas Thorpe, Ye Tian, Shu-Chuan Tseng
*SEMDIAL BOARD CHAIRS:*
Ellen Breitholtz (University of Gothenburg))
Julian Hough (Queen Mary University of London)
http://semdial.org/
Eleni Gregoromichelaki
Professor of Linguistics
Linguistics, Logic and Theory of Science unit
Department of Philosophy, Linguistics, Theory of Science (FLoV)
University of Gothenburg
Room: C539, Renströmsgatan 6
Tel.: +46 31-786 52 33
Dear Colleagues,
Will you post this to your network, your PhD students and other potentially
interested parties? Letters are not initially required with the application.
Thanks
Lyn
-------
The Natural Language Processing Program (nlp.ucsc.edu) in the Computer
Science and Engineering Department at the University of California, Santa
Cruz (UCSC) invites applications for the Natural Language Processing
Postdoctoral Researcher, under the direction of Professor Marilyn Walker.
We seek outstanding applicants with research expertise in all areas of
Natural Language Processing (NLP). The NLP Postdoctoral Researcher will be
expected to contribute to the research and teaching profile of the NLP
group. We also expect the successful candidate to support graduate students
and other Postdoctoral Scholars as a peer
Feel free to contact me at nlp(a)ucsc.edu with any questions.
Applications are open now, full consideration will be given to applications
submitted by July 15th, 2022 for a start date of September 1st. For
details, and to apply, go here: https://recr
<https://recruit.ucsc.edu/JPF01330>uit.ucsc.edu/JPF01330
<https://recruit.ucsc.edu/JPF01330>
--
Professor Marilyn Walker
Fellow of the Association for Computational Linguistics
Program Director, NLP MS Program, https://nlp.ucsc.edu/
Natural Language and Dialogue Systems Lab
Department of Computer Science and Engineering
Baskin School of Engineering
University of California Santa Cruz
users.soe.ucsc.edu/~maw
--
Professor Marilyn Walker
Fellow of the Association for Computational Linguistics
Program Director, NLP MS Program, https://nlp.ucsc.edu/
Natural Language and Dialogue Systems Lab
Department of Computer Science and Engineering
Baskin School of Engineering
University of California Santa Cruz
users.soe.ucsc.edu/~maw
CeADAR (Ireland's Centre for Applied AI: https://ceadar.ie) at the UCD
School of Computer Science (https://ucd.ie/cs/) is seeking to appoint
postdoctoral researchers at any level of experience until *September 2023*
to work on the TRANSPIRE project in *Dublin, Ireland*.
You will perform novel research on Machine Learning, AI and Natural
Language Processing for legal and regulatory texts. The key research focus
of the project relates to analysis, classification and knowledge extraction
for these texts in a transparent way. As such, a core priority will be a
body of research on explainable and/or interpretable models for legal text
analysis.
TRANSPIRE is funded under the Disruptive Technologies Innovation Fund
(DTIF) and is a collaboration with two industry partners: Corlytics (
https://corlytics.com) and Version 1 (https://version1.com). As such, a
core feature of the project is to work closely with domain experts who will
both inform the research and contribute domain expertise towards training
the models.
Candidates should have research experience in one or more of Natural
Language Processing, Computational Linguistics, Information Retrieval, Text
Analytics (including the use of Machine Learning, Deep Learning and/or
Explainable AI for textual data).
For application details and salary scales please see:
- *Research Fellow* (≥4 years postdoctoral research experience): click here
<https://my.corehr.com/pls/ucdrecruit/erq_search_version_4.start_search_with…>
(or visit https://www.ucd.ie/workatucd/jobs/ and search for job reference
014723)
- *Postdoctoral Researcher* (<4 years postdoctoral research experience)
click here
<https://my.corehr.com/pls/ucdrecruit/erq_search_version_4.start_search_with…>
(or visit https://www.ucd.ie/workatucd/jobs/ and search for job reference
014722)
Please note that due to institutional rules, if you wish to be considered
for both positions you will need to apply for both separately.
The closing date for applications is *Friday July 15th 2022*.
For informal enquiries about these roles, please contact david.lillis(a)ucd.ie
Feel free to forward this to talented researchers in your network who may
be interested.
Dear colleagues,
We cordially invite you to the 29th International Conference on
Head-Driven Phrase Structure Grammar (July 29-30, 2022), as well as the
Workshop on Computational Linguistics on East Asian Languages (July 31,
2022). The conference and the workshop will be held online.
The program is available on the conference website, where you will also
find registration information: https://hpsg2022.github.io/program.html
Please note that the times are given in Japan Standard Time (in order to
transcribe them into your local time: https://savvytime.com/converter/jst).
In order to allow the widest possible exchange between participants
spread all over the world, the regular presentations will be
pre-recorded and only the discussion sessions will take place in real
time (on Zoom). The invited talks will take place in real time. The
videos of the regular presentations will be available on a Discord
server. When you register, you will receive a message that contains an
invitation link to the server, as well as the Zoom session URLs.
Registration to the conference is free of charge.
We look forward to meeting you all for exciting discussions.
Elodie Winckel (Program Committee Chair, hpsg22(a)easychair.org).
Madrid – 3-year PhD position
The UNED IR & NLP group has an open 3-year PhD position. The successful candidate is expected to work on the CLARA: artifiCial inteLligence observAtory foR spAnish, that has the aim of measuring the gap in Artificial Intelligence between English and Spanish. The project focuses on monitoring the comparative state of the art of Natural Language Processing in English and Spanish, as well as quantifying the comparative adoption and use of Artificial Intelligence solutions in English and Spanish by citizens and organizations.
As part of this team, the candidate will research in evaluation metrics and frameworks. Also, the candidate will collaborate in the design and development of the evaluation framework EvALL 2.0 (see EvALL 1.0 at www.evall.uned.es<http://www.evall.uned.es>), an online evaluation service for Artificial Intelligence systems.
* Candidate profiles *
* Academic background (university degree, preferably master) in computer science or related discipline.
* Experience developing Python applications.
* Excellent programming skills.
* Collaborative work skills.
* Fluent in English (knowledge of Spanish is a plus).
* Terms and conditions *
Location: NLP&IR UNED, Madrid, Spain
Duration: 3 years (1+1+1)
Salary: 30.000 €
Context: CLARA: artifiCial inteLligence observAtory foR spAnish
* Application *
Please send an email to julio(a)lsi.uned.es and jcalbornoz(a)lsi.uned.es<mailto:jcalbornoz@lsi.uned.es> titled “Programador de Django y Python” and include CV, names of two references and a brief motivation letter stating your interests and past experience
The position is open until filled. More details in the official call:
https://www2.uned.es/bici/Curso2021-2022/220404/24-1.htm#9.-_____
* More about us *
The UNED NLP & IR group is a leading research group (of around 30 members) in the areas of Natural Language Processing and Information Retrieval. See nlp.uned.es for details.
AVISO LEGAL. Este mensaje puede contener información reservada y confidencial. Si usted no es el destinatario no está autorizado a copiar, reproducir o distribuir este mensaje ni su contenido. Si ha recibido este mensaje por error, le rogamos que lo notifique al remitente.
Le informamos de que sus datos personales, que puedan constar en este mensaje, serán tratados en calidad de responsable de tratamiento por la UNIVERSIDAD NACIONAL DE EDUCACIÓN A DISTANCIA (UNED) c/ Bravo Murillo, 38, 28015-MADRID-, con la finalidad de mantener el contacto con usted. La base jurídica que legitima este tratamiento, será su consentimiento, el interés legítimo o la necesidad para gestionar una relación contractual o similar. En cualquier momento podrá ejercer sus derechos de acceso, rectificación, supresión, oposición, limitación al tratamiento o portabilidad de los datos, ante la UNED, Departamento de Política Jurídica de Seguridad de la Información<https://www.uned.es/dpj>, o a través de la Sede electrónica<https://sede.uned.es/> de la Universidad.
Para más información visite nuestra Política de Privacidad<https://descargas.uned.es/publico/pdf/Politica_privacidad_UNED.pdf>.
The 9th Argument Mining Workshop
Special Theme: Argument Mining in Real-World Applications
Shared task: Automated Assessment of Argument Validity and Novelty https://phhei.github.io/ArgsValidNovel/
###############################################################
NEWS WITH RESPECT TO THE PREVIOUS CFP:
Extended deadline: July 18th 2022
Invited talk: Hans Hoeken (University of Utrecht), “Mining for Persuasive Ingredients: What’s the Right Mix?”
Panel on applications of Argument Mining:
- Legal: Laura Alonso Alemany (University of Cordoba)
- Finance: Chung-Chi Chen (AIST)
- Education: Beata Beigman Klebanov (ETS)
- E-governance: Joonsuk Park (University of Richmond)
- Business: Michael Yeomans (Imperial College London)
Workshop date: October 17
##################################################################
Location: In conjunction with COLING 2022 in Gyeongju, Republic of Korea - in a hybrid format
Webpage: https://argmining-org.github.io/2022/
Contact: argmining.org(a)gmail.com <mailto:argmining.org@gmail.com>
Date: October 17
Final Call for Papers - Deadline extension (apologies for cross-posting)
Argument mining (also known as "argumentation mining") is a growing research area within computational linguistics. At its heart, argument mining involves the automatic identification of argumentative structures in free text, such as the conclusions, premises, and inference schemes of arguments, as well as their pro- and con-relations. To date, researchers have investigated argument mining in many genres, such as legal documents, product reviews, news articles, online debates, Wikipedia articles, essays, academic literature, tweets, and dialogues. In addition, argument quality assessment and generation are also important problems. Argument mining gives rise to various practical applications of great importance. In particular, it provides methods that can find and visualize the main pro and con arguments in written text and dialogue and that enable argument search on the web for a topic of interest. In educational contexts, argument mining can be applied to written and diagrammed arguments for instructing and assessing students' critical thinking. In information retrieval, argument mining is expected to play a salient role in the emerging field of conversational search.
We are looking for diverse research work on argument mining in real-world applications from various domains. Real-world applications include argument analysis in education, finance, law, public policy, and other social sciences, argument web search, opinion analysis in customer reviews, argument analysis in meetings, and scientific writing.
CALL FOR PAPERS
ArgMining 2022 invites the submission of long and short papers on substantial, original, and unpublished research in all aspects of argument mining. The workshop solicits LONG and SHORT papers for oral and poster presentations, as well as DEMOS of argument mining systems and tools.
The topics for submissions include but are not limited to:
• Automatic identification of argument components (premises and conclusions or more fine-grained), and relations between arguments and counterarguments (support and attack or more fine-grained) within/across documents
• Automatic assessment of properties of arguments and argumentation, such as argumentation schemes, stance, quality, and persuasiveness
• Automatic synthesis of arguments and their components, including the consideration of discourse goals (e.g., stages of a critical discussion or rhetorical strategies) and the possibly needed preceding analyses
• Creation and evaluation of argument annotation schemes, relationships to linguistic and discourse annotations, (semi-) automatic argument annotation methods and tools, and creation of argumentation corpora
• Management of spoken and transcribed dialogue, argument mining from such data, including additional challenges posed by real-time processing
• Combination of NLP methods and AI models developed for argumentation, such as abstract and structured argumentation frameworks
• Combination of information retrieval methods with argument mining, e.g. in order to build the next generation of argumentative (web) search engines
• Use of argument mining for studying research questions from education, finance, law, public policy, digital humanities, and any other social sciences
• Reflection on the ethical aspects and societal impact of argument mining methods
Submission Information
Three types of papers can be submitted: Long papers (8 pages + references), short papers (4 pages + references), and demo papers (4 pages + references). Demo papers must include a URL to a running demo. Accepted papers will be given an additional page to account for the reviewers' comments. All papers will be treated equally in the workshop proceedings. The workshop follows ACL’s policies for submission, review, and citation. Moreover, authors are expected to adhere to the ethical code set out in the ACL Code of Ethics. Submissions that violate any of the policies will be rejected without review.
Please use the COLING 2022 style sheets for formatting your paper: https://coling2022.org/
Submission URL: https://www.softconf.com/coling2022/AM_2022
The workshop is running a double-blind review process. In preparing your manuscript, do not include any information which could reveal your identity, or that of your co-authors. The title section of your manuscript should not contain any author names, email addresses, or affiliation status. If you do include any author names on the title page, your submission will be automatically rejected. In the body of your submission, you should eliminate all direct references to your own previous work. That is, avoid phrases such as "this contribution generalizes our results for XYZ". Also, please do not disproportionately cite your own previous work. In other words, make your submission as anonymous as possible. We need your cooperation in our effort to maintain a fair, double-blind reviewing process - and to consider all submissions equally. Double Submission Papers that have been or will be submitted to other venues should indicate this at submission time. Upon acceptance at either event, the submission must be withdrawn from the other. To save reviewers' efforts, avoid submitting (or withdraw early) papers that are on track to be accepted elsewhere.
Important Dates
• Submission due: July 18, 2022
• Notification of acceptance: August 25, 2021
• Camera-ready papers due: September 5, 2022
• Workshop: TBD: COLING 2022 October 12-17, 2022
All deadlines are 11:59 pm UTC -12h (“anywhere on Earth”).
ORGANIZERS
Gabriella Lapesa (University of Stuttgart)
Jodi Schneider (University of Illinois Urbana-Champaign)
Yohan Jo (Amazon)
Sougata Saha (University at Buffalo, New York)
SHARED TASK: AUTOMATED ASSESSMENT OF ARGUMENT VALIDITY AND NOVELTY
Organizers: Philipp Heinisch, Philipp Cimiano (University of Bielefeld), Anette Frank, and Juri Opitz (University of Heidelberg)
Webpage: https://phhei.github.io/ArgsValidNovel/
Brief description
In recent years, there have been increased interests in understanding how to assess the
quality of arguments systematically. To foster more research on this topic in the community, we plan to organize a task consisting of assessing whether computational models can reliably assess the validity and novelty of a conclusion given a set of the textual premises.
Tasks
Participants can choose either Task A or Task B, or both.
Task A: The first task consists of a binary classification task along the dimensions of novelty and validity, classifying a conclusion as being valid/novel or not given a textual premise.
Task B: The second subtask will consist in comparing two conclusions in terms of validity / novelty.
2nd Call for Papers - CODI 2021: 2nd Workshop on Computational Approaches to Discourse
https://sites.google.com/view/codi-2021
Held in conjunction with EMNLP 2021 November 10-11, 2021
Update: Note that we accept double submissions, see the dedicated section below.
Important information: The CODI workshop organization should be hybrid, following the EMNLP program chairs’ decision: “EMNLP 2021 is currently officially scheduled to be held in hybrid mode, online and in Punta Cana, in the Dominican Republic. ”. The 2-days workshop will take place on November 10 and 11.
**Aims and scope**
The last five years have seen a dramatic improvement in the ability of NLP systems to understand and produce words and sentences. This development has created a renewed interest in discourse problems as researchers move towards the processing of long-form text and conversations. There is a surge of activity in discourse parsing, coherence models, text summarization, corpora for discourse level reading comprehension, and discourse related/aided representation learning, to name a few. At this juncture, we envision that a workshop that brings together discourse experts and upcoming researchers will catalyze the speed and knowledge needed to solve such problems, as well as serve as a forum for the discussion of suitable datasets and reliable evaluation methods.
The previous workshops on discourse in machine translation (DiscoMT), linking lexical, sentential and discourse semantics (LSDSem), discourse structure in natural language generation (DSNNLG), discourse parsing and treebanking (DisRPT) and coreference (CORBON/ CRAC), have shown that there is considerable interest and success in bringing together the community working on specific problems. We believe that the discourse community will also benefit from a general forum where work ranging from corpus development/analysis to computational models, and evaluation is discussed, and desiderata can be drawn for future progress.
The Workshop on Computational Approaches to Discourse (CODI) brings together researchers interested in all aspects of discourse and its computational modeling. The first CODI workshop was held at EMNLP 2020 and showcased diverse discourse research (see the papers presented: https://codi-workshop.github.io/accepted-papers/).
This year, the workshop will also host two shared tasks:
- CODI-CRAC - Anaphora Resolution in Dialogues: https://competitions.codalab.org/competitions/30312
- CODI-DISRPT2021- Discourse Relation Parsing and Treebanking: https://sites.google.com/georgetown.edu/disrpt2021
Please visit the corresponding websites for more information.
**Topics of interest**
We welcome symbolic and probabilistic approaches, corpus development and analysis, as well as machine and deep learning approaches to discourse. We appreciate theoretical contributions as well as practical applications, including demos of systems and tools. The goal of the workshop is to provide a forum for the community of NLP researchers working on all aspects of discourse.
Topics of interest include, but are not limited to:- discourse structure
- discourse connectives
- discourse relations
- annotation tools and schemes for discourse phenomena
- corpora annotated with discourse phenomena
- discourse parsing
- cross-lingual discourse processing
- cross-domain discourse processing
- anaphora and coreference resolution
- event coreference
- argument mining
- coherence modeling
- discourse and semantics
- discourse in applications such as machine translation, summarization, etc.
- evaluation methodology for discourse processing
**Submissions**
We solicit four categories of papers: (1) regular workshop papers, (2) demos, (3) extended abstracts and (4) shared tasks papers. Only regular workshop papers, shared task papers and demos will be included in the proceedings as archival publications.
Regular papers must describe original unpublished research. Long papers may consist of up to 8 pages of content, plus unlimited pages for references. Short papers can have up to 4 pages, plus unlimited pages for references.
Demo submissions may describe systems, tools, visualizations, etc., and may consist of up to 4 pages, plus unlimited pages for references.
Accepted long, short, and demo papers will be presented orally.
Extended abstracts can describe work in progress or those already published elsewhere. These may be two pages long (without references). Extended abstracts are non-archival. They will be presented orally, and included in the workshop program and handbook, but will not appear in the workshop proceedings.
For shared task papers, please refer to the corresponding websites:- CODI-CRAC: https://competitions.codalab.org/competitions/30312#learn_the_details-overv…
- CODI-DISRPT2021: https://sites.google.com/georgetown.edu/disrpt2021/submission?authuser=0
Shared task papers will be presented during the dedicated sessions, either orally or as posters. They will be included in the workshop proceedings.
Final versions of all types of papers will be given one additional page of content.
**Double submission**
We allow for double submissions. Please indicate during submission to which other conference or workshop your work has been submitted.
We may also invite authors of papers accepted to the conferences (e.g. EMNLP, ACL) including Findings to present their work at the workshop. Please indicate whether your paper has been accepted to e.g. ACL during submission, or let us know by email that your paper has been accepted elsewhere (including Findings) upon notification. These papers will not be part of the proceedings of the workshop.
**Submission website**
All submissions must follow the EMNLP 2020 formatting instructions described here: https://2021.emnlp.org/call-for-papers/style-and-formatting
Please submit your papers using the link indicated on our website.
**Important dates**
* 18 May, 2021: 1st Call for Workshop Papers * 15 June, 2021: 2nd Call for Workshop Papers * 5 July, 2021: Anonymity period starts * 15 July, 2021: 3rd Second Call for Papers * 5 Aug, 2021: Workshop Papers Due (long, short, demo, extended abstracts) * 5 Sept, 2021: Notification of Acceptance * 15 Sept, 2021: Camera-ready papers due * Nov 10-11, 2021: Workshop Date
Please check the dedicated websites to get information about the deadlines for the two shared tasks.
All deadlines are 11.59 pm UTC -12h (“anywhere on Earth”).