Call for Interest: DISRPT 2025 - Shared Task on Discourse Relation Parsing and Treebanking
Call for expression of interest: DISRPT 2025 - Shared Task on Discourse Relation Parsing and Treebanking 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 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. For datasets which have treebanks, we will evaluate segmentation 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! This will make our replication work easier, but more importantly, it will simplify using such a model and test the robustness of your solution!
At this time we are calling for expressions of interest to participate. Registered participants will be added to our mailing list and receive updates as soon as data is made available. Please join us on: disrpt2025_participants@googlegroups.com
**Important dates:**
May 16 2025 – sample data release
June 16 2025 – training data release
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
**Information:**
Contact the organizers:disrpt_chairs@googlegroups.com
Official website: https://sites.google.com/view/disrpt2025/
Google group for participants, please join us on: disrpt2025_participants@googlegroups.com
**Organization:**
Peter Bourgonje (Universität Potsdam, Germany)
Chloé 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)