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 in different areas but facing similar issues with coherence and cohesion, document-level structure, long text, and long context.
In 2025 at EMNLP, we organized the first joint CODI-CRAC workshop. The CODI workshop has provided a platform for a broad range of research at the discourse level, while the CRAC workshop has been a primary venue for exploring computational modeling of reference, anaphora, and coreference.
In 2026, the second edition of CODI-CRAC corresponds to the 7th CODI workshop and the 10th 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 planned as a 1-day event that brings together different subcommunities. It will feature invited talks, regular papers, and the 2026 CRAC shared task. We also accept papers accepted at other major conferences for non-archival presentation, including Findings papers.
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 pre-training tasks
Long-text modeling and generation
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.
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.
CODI-CRAC considers for publication papers rejected at one of the main conferences, authors will have to submit both the paper and the reviews as a supplementary pdf file. If modifications have been made since the original submission, please submit an additional file describing briefly the modifications made. The organizers will decide on the acceptance of the papers based on the quality of the paper and its fit with the workshop.
As a reminder, CODI-CRAC also invites presentations of paper accepted at another main conference. They will be included in the workshop program and handbook, but will not appear in the workshop proceedings.
All submissions must be anonymous and follow the ACL 2026 formatting instructions described here: https://aclrollingreview.org/cfp.
To appear
CRAC 2026 Shared Task: https://ufal.mff.cuni.cz/corefud/crac26
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
Student D&I Grant application: May 5, 2026
Camera-ready paper due: May 12, 2026
Pre-recorded video due: June 4, 2026
Workshop date: July 3 or 4, 2026
All deadlines are 11.59 pm UTC -12h ("anywhere on Earth").