From Chloe.Braud at irit.fr Fri Jul 4 10:14:47 2025 From: Chloe.Braud at irit.fr (=?utf-8?q?Chlo=C3=A9_Braud?=) Date: Fri, 04 Jul 2025 12:14:47 +0200 Subject: [Rstlist] =?utf-8?q?Third_call_for_Participation=3A_DISRPT_2025_?= =?utf-8?q?Shared_Task_on_Discourse_Relation_Parsing_and_Treebanking?= Message-ID: <176a52-6867a980-5d-14a6d6a0@195043679> ??Call for Participation: DISRPT 2025 Shared Task on Discourse Relation Parsing and Treebanking.? ?? training data has been released and the submission is now open!? https://softconf.com/emnlp2025/disrpt2025/ In conjunction with CODI-CRAC & EMNLP 2025 - Suzhou, China, Nov. 5-9. This year, we are organizing the fourth edition of the DISRPT shared task on discourse processing across formalisms, for a variety of languages and genres, with three subtasks: ? * Task 1: Discourse segmentation * Task 2: Connective identification * Task 3: Relation classification ? We will provide training, development and test datasets from (almost) all available languages? in RST / eRST, SDRT, PDTB, ISO 24617, and discourse dependencies, using a uniform format. Because different corpora, languages, and frameworks use different guidelines, the shared task will promote the design of flexible methods for dealing with various guidelines, and will help to push forward the discussion of converging standards for discourse units. We will evaluate segmentation and connective detection in two different scenarios: with and without gold syntax. An automatically parsed version is provided for all corpora without a gold parse.? ? This year, the shared task will feature:? * The inclusion of?more frameworks, with datasets from: RST / eRST, SDRT, PDTB, ISO 24617, and discourse dependencies * The inclusion of?new corpora and new languages, some of them kept a surprise! * A?unified set of labels for the discourse relations, to make easier the evaluation across datasets * A new constraint:?only one multilingual model should be submitted per task, and it should be small (4B parameters max)! This will make our replication work easier, but more importantly, it will simplify using such a model and test the robustness of your solution.? We?re excited to announce the release of the?training data for the DISRPT 2025 Shared Task! You can now access the data, format documentation, and tools on our GitHub ??https://github.com/disrpt/sharedtask2025 The data covers?five discourse frameworks ? RST / eRST, PDTB, SDRT, and Discourse Dependencies ? across?14 languages: Basque, Chinese, Czech, Dutch, English, Farsi, French, German, Italian, Portuguese, Russian, Spanish, Thai and Turkish Thai. We invite researchers and teams interested in participating to register now. Registered participants will be added to our mailing list and receive all future updates. ? The?full testing data will be released on?July 14, 2025 ? stay tuned! To join the mailing list and stay informed, please email us at: ??disrpt_chairs at googlegroups.com? Let us know you're interested ? we?d love to have you on board! **Important dates** ? * May 16 2025 ? Sample data release * June 17 2025 ? Training data release [NOW] * July 14 2025 ? Test data release * August 1 2025 ? System + paper submissions due * September 12 2025 ? Notification of acceptance * September 19 2025 ? Camera ready papers * November 8-9 2025 ? CODI at EMNLP All deadlines are 11.59 pm UTC -12h (AoE, "Anywhere on Earth"). ? **Information:** ? Contact the organizers:?disrpt_chairs at googlegroups.com? Official website:?https://sites.google.com/view/disrpt2025/ ?????Google group for participants, please join us on:?disrpt2025_participants at googlegroups.com ? ? **Organization:** ? Chlo? Braud (CNRS - IRIT, University of Toulouse, France) Chuyuan Li (University of British Columbia, Canada) Janet Yang Liu (LMU Munich, Germany) Philippe Muller (CNRS - University of Toulouse, France) Amir Zeldes (Georgetown University, Washington DC, USA) -------------- next part -------------- An HTML attachment was scrubbed... URL: From Chloe.Braud at irit.fr Fri Jul 4 10:00:09 2025 From: Chloe.Braud at irit.fr (=?utf-8?q?Chlo=C3=A9_Braud?=) Date: Fri, 04 Jul 2025 12:00:09 +0200 Subject: [Rstlist] =?utf-8?q?CODI_CRAC_2025_Workshop=3A_third_joint_call_?= =?utf-8?q?for_papers?= Message-ID: <176a53-6867a600-6d-28bf6280@233833673> CODI CRAC 2025 Workshop: joint call for papers ? November 5-9 2025 - EMNLP 25 - Suzhou, China ? We are pleased to announce that we are organizing in 2025 the first joint CODI-CRAC workshop that will be held during EMNLP! More information on:?https://sites.google.com/view/codi-crac2025/? ? Deadline for CODI CRAC papers: July 30 2025 ? ? We will host 2 shared tasks, the CRAC and the DISRPT shared tasks. More information on: - CRAC shared task:?https://ufal.mff.cuni.cz/corefud/crac25? - DISRPT shared task:? https://sites.google.com/view/disrpt2025/?Aims and scope ? The last few years have seen a dramatic improvement in the ability of NLP systems and Large Language Models to understand and produce words, sentences and in some cases longer texts. This development has created a renewed interest in discourse problems as researchers move towards the processing of long-form documents and conversations. There is a surge of activity in discourse pretraining tasks, coherence models, summarization for long texts and conversations, corpora for discourse level reading comprehension and formal parsing, as well as discourse related/aided representation learning, to name a few. ? Discourse, roughly the interactions of context, form and meaning above the sentence level, is at the intersection of many areas in Computational Linguistics and NLP, since it is concerned with all levels of linguistic representation, allowing the modeling of textual coherence and inference leveraging long-distance links within documents.It thus brings together researchers working on different areas but facing similar issues with coherence and cohesion, document-level structure, long text and long context. ? In 2025, we organize the first joint CODI-CRAC workshop. The CODI workshop has been a forum for a broad range of work at the discourse level. The CRAC workshop has been a primary venue for researchers interested in the computational modeling of reference, anaphora, and coreference. Together, these workshops have catalyzed work to advance research on discourse level problems and have served as a forum for the discussion of suitable datasets and reliable evaluation methods. ? This joint edition corresponds to the 6th CODI workshop and the 8th CRAC workshop. It will welcome contributions from all the areas below, including state of the art textual NLU and NLG work using LLMs, as well as classic structured work on automatic discourse analysis -- corresponding to challenging tasks such as coreference resolution or discourse parsing -- to encourage interaction between communities. The workshop is set to host the fourth edition of the DISRPT shared task on Discourse Relation Parsing and Treebanking and the fourth edition of the CRAC shared task on Multilingual Coreference Resolution. ? The workshop is planned as a 1 day event which brings together different subcommunities. It will feature invited talks and regular papers. We also accept papers accepted at other major conferences for non-archival presentation, including Findings papers. ?Topics of interest ? We welcome papers on 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 - discourse pretraining tasks - long-text modeling and generation ?Submissions ? We solicit three categories of papers: regular (long and short) workshop papers, demos and extended abstracts. Only regular workshop papers and demos will be included in the proceedings as archival publications. Double submission of papers is allowed, but this information will need to be disclosed at submission time. ? 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 be 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. ? Each submission can contain unlimited pages for Appendices but the paper submissions need to remain fully self-contained, as these supplementary materials are completely optional, and reviewers are not even asked to review them. ? Extended abstracts can describe work in progress. These may be two pages long (without references). Extended abstracts are non-archival. They will be included in the workshop program and handbook, but will not appear in the workshop proceedings.Paper accepted or rejected at one of the main conferences ? We also invite presentations of paper accepted at another main conference, a specific deadline and submission process will be communicated later on. They will be included in the workshop program and handbook, but will not appear in the workshop proceedings. We also fast-track ARR papers with reviews, with timeline TBA. ?Submission website ? All submissions must be anonymous and follow the EMNLP 2025 formatting instructions described here: https://aclrollingreview.org/cfp ? Submission websites: * CODI:?https://softconf.com/emnlp2025/codi2025/ * DISRPT:?https://softconf.com/emnlp2025/disrpt2025/ * CRAC:? https://softconf.com/emnlp2025/crac2025/?Schedule ? - July 30 2025: CODI CRAC papers due - September 5 2025:Notification of acceptance - September 19 2025:Camera ready deadline - November 8-9 2025-:CODI-CRAC workshop ? All deadlines are 11.59 pm UTC -12h ("anywhere on Earth"). ?Invited Speakers ? - Tanya Goyal, Cornell University. - Nancy F. Chen, Institute of Infocomm Research (I2R), A-STAR, Singapore ?Organizers ? - Chlo? Braud, CNRS-IRIT - Christian Hardmeier, IT University of Copenhagen - Chuyuan (Lisa) Li,? University of British Columbia - Jessy Li, University of Texas, Austin - Sharid Lo?iciga, University of Gothenburg - Vincent Ng, University of Texas at Dallas - Michal Nov?k, Charles University, Prague - Maciej Ogrodniczuk, Institute of Computer Science, Polish Academy of Sciences - Massimo Poesio, Queen Mary University of London and University of Utrecht - Sameer Pradhan, University of Pennsylvania and cemantix - Michael Strube, Heidelberg Institute for Theoretical Studies - Amir Zeldes, Georgetown University, Washington DC ? To contact the organizers, please send an email to:?codi-crac-workshop at googlegroups.com? -------------- next part -------------- An HTML attachment was scrubbed... URL: