The aim of the workshop is to provide a forum where work on all aspects of computational work on anaphora resolution and annotation, including both coreference and types of anaphora such as bridging references resolution and discourse deixis, can be presented.
TOPICS
The workshop will welcome submissions describing theoretical and applied computational work on anaphora/coreference resolution. Topics of interest include but are not limited to:
- coreference resolution for less-researched languages
- annotation and interpretation of anaphoric relations, including relations other than identity coreference (e.g., bridging references)
- investigation of difficult cases of anaphora and their resolution
- coreference resolution in noisy data (e.g. in social media)
- new applications of coreference resolution
- Universal Anaphora
PAPER CATEGORIES
CRAC 2021 has the goal of a broad technical program. Thus, we welcome papers in the following categories:
- Research papers (theoretical computational linguistics, empirical/data-driven approaches, paradigms/techniques/strategies, analysis papers, resources and evaluation, negative result)
- Survey papers (surveys a popular or emerging area of anaphora/coreference resolution)
- Position papers (presents one side of an arguable opinion about an issue)
- Challenge papers (a challenge to the field in terms of setting out a goal for the next 5/10/20 years)
- Demo papers (systems, tools, visualizations)
- Extended abstracts (describes work in progress)
Research papers, survey papers, position papers, and challenge papers can have up to 9 pages of content for long papers and up to 4 pages of content for short papers, plus an unlimited number of pages for references. Demo papers can have up to 4 pages of content plus an unlimited number of pages for references. Extended abstracts can have up to 2 pages of content plus an unlimited number of pages for references.
All accepted papers will be published in the workshop proceedings.
SPECIAL THEME
A special theme of the 2021 edition of the workshop is the Universal Anaphora (UA) framework – a unified markup scheme applicable to multiple languages, reflecting common cross-linguistic understanding of reference-related phenomena. This theme was motivated by the recent successes of the development of Universal Dependencies. As with Universal Dependencies, the UA framework aims to facilitate referential analysis of similarities and idiosyncracies among typologically different languages, support comparative evaluation of anaphora resolution systems and enable comparative linguistic studies. In addition, the workshop will include a panel discussion on possible improvements of the initial framework based on the outcomes of the shared task.
IMPORTANT DATES
Workshop papers due: Aug 12, 2021
Notification of acceptance: Sep 5, 2021
Camera-ready papers due: Sep 15, 2021
Workshop date: Nov 11, 2021