Call for Participation
This year, we're organizing DISRPT 2023 as a shared task on discourse processing across formalisms, for a variety of languages and genres. It is the second iteration of a cross-formalism shared task on discourse analysis, with three subtasks this year:
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, SDRT, and PDTB, 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.
Shared Task Data and Formats:
Data for the shared task is released via GitHub together with format documentation and tools:
https://github.com/disrpt/sharedtask2023
See here for more information about the previous 2019 and 2021 shared tasks:
Tentative Schedule:
25 January 2023 – Sample data released
22 February 2023 – Train / dev data release
15 April 2023 – Test data release
8 May 2023 – Submission of system and paper
22 May 2023 - Notification of acceptance
5 June 2023 - Camera-ready paper due
July 2023 between 9th and 14th - CODI Workshop at ACL
Submission link: TBA
Information:
Contact the organizers: disrpt_chairs@googlegroups.com
Official website: https://sites.google.com/georgetown.edu/disrpt2023
Google group for participants, please join us on: disrpt2023_participants@googlegroups.com
Discord group for participants, please join us on: https://discord.gg/JDdjhXaK
Organization:
Amir Zeldes (Georgetown University, Washington, DC, USA)
Janet Liu (Georgetown University, Washington, DC, USA)
Philippe Muller (IRIT, University of Toulouse, Toulouse, France)
Chloé Braud (IRIT, CNRS, Toulouse, France)
Laura Rivière (IRIT, University of Toulouse, Toulouse, France)
Attapol Te Rutherford (Faculty of Arts Chulalongkorn University, Bangkok, Thaïland)