*apologies for cross-postings*

Joint CODI CRAC 2026 Workshop: call for papers

�

July 2026 - ACL 2026 - San Diego, USA

�

We are pleased to announce that we are organizing the second joint CODI-CRAC workshop which will be held during ACL 2026! More information at:

�

https://sites.google.com/view/codi-crac2026/home https://sites.google.com/view/codi-crac2026/ �

�

CODI-CRAC is officially endorsed by SIGDial, the ACL Special Interest Group on Discourse and Dialogue.

�

Deadline for CODI CRAC papers: March 20 2026

�

The workshop will also host the CRAC shared task. More information at:

�

- CRAC shared task: https://ufal.mff.cuni.cz/corefud/crac26 https://ufal.mff.cuni.cz/corefud/crac26

Aims and scope

�

Recent breakthroughs in NLP and Large Language Models have dramatically expanded our systems’ abilities to interpret and generate not just sentences, but whole documents and conversations. This shift has renewed interest in discourse-level challenges, driving new work on inter-sentential phenomena, coherence modeling, long-form summarization, discourse-aware representation learning, and large-scale resources for discourse understanding and parsing.

�

Discourse sits at the intersection of many NLP subfields, as it is where context, structure, and meaning come together beyond single sentences. Discourse shapes how we capture coherence, cohesion, and inference across long texts, and brings together researchers tackling the shared challenges of document structure, long-range dependencies, and the requirements of extended context.

�

In 2025, we organized the first joint CODI-CRAC workshop. The CODI workshop on Computational Approaches to Discourse has been a forum for a broad range of work at the discourse level. The CRAC workshop on Computational Models of Reference, Anaphora and Coreference has been a primary venue for researchers interested in the computational modeling of reference phenomena. Together, these workshops have catalyzed work to advance research on discourse-level problems and have served as a forum for discussing suitable datasets and reliable evaluation methods.

�

This joint edition corresponds to the 7th CODI workshop and the 9th 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 5th edition of the CRAC shared task on Multilingual Coreference Resolution.

�

The workshop is planned as a 1-day event that brings together different subcommunities. It will feature regular papers and invited talks by Ruihong Huang (Texas A&M University) and Philippe Laban (Microsoft Research). 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

Double submission of papers is allowed, but this information will need to be disclosed at submission time.

�

We solicit three categories of papers: �

* (1) Regular workshop papers �

* (2) Demos

* (3) Extended abstracts

Only regular workshop papers and demos will be included in the proceedings as archival publications. Extended abstracts are non-archival and will be included in the workshop program and handbook, but will not appear in the workshop proceedings.

1- 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.

2- Demo submissions may describe systems, tools, visualizations, etc., and may consist of up to 4 pages, plus unlimited pages for references.

3- Extended abstracts can describe work in progress. They 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.

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.

Final versions of all types of papers will be given one additional page of content.

Paper accepted or rejected at one of the main conferences

�

We also invite presentations of papers accepted at another main conference. 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 existing reviews.

Submission website

�

All submissions must be anonymous and follow the ACL 2026 formatting instructions described here: https://aclrollingreview.org/cfp https://aclrollingreview.org/cfp �

�

Submission website:

* CODI-CRAC: https://softconf.com/acl2026/codi-crac2026/ https://softconf.com/acl2026/codi-crac2026/ �

Schedule

Important dates for the workshop are listed below:

* CODI-CRAC papers due: March 20 * Pre-reviewed ARR fast-track (with reviews, can be accepted or rejected): April 5 � * Notification of acceptance: April 28, 2026 * Grant application: May 5, 2026 * Camera-ready paper due: May 12, 2026 * Pre-recorded video due: June 4, 2026 * Workshop dates: July 3 or 4, 2026

�

�All deadlines are 11.59 pm UTC -12h ("anywhere on Earth").

Invited Speakers

�

- Ruihong Huang, Texas University

- Philippe Laban, Microsoft Research

Organizers

�

- Chloé Braud, CNRS-IRIT

- Christian Hardmeier, IT University of Copenhagen

- Chuyuan (Lisa) Li, � University of British Columbia

- Jessy Li, University of Texas, Austin

- Sharid Loáiciga, University of Gothenburg

- Vincent Ng, University of Texas at Dallas

- Michal Novák, Charles University, Prague

- Maciej Ogrodniczuk, Institute of Computer Science, Polish Academy of Sciences

- Massimo Poesio, Queen Mary University of London and University of Utrecht

- Michael Strube, Heidelberg Institute for Theoretical Studies

- Amir Zeldes, Georgetown University, Washington DC

�

To contact the organizers, please send an email to: mailto:codi-crac-workshop@googlegroups.com codi-crac-workshop@googlegroups.com �

�