November 11 Punta Cana, Dominican Republic Collocated with EMNLP 2021
OBJECTIVES 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 (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 ● 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.
DATES ● Workshop papers due: Aug 5, 2021 ● Notification of acceptance: Sep 5, 2021 ● Camera-ready papers due: Sep 15, 2021 ● Workshop date: Nov 11, 2021
SUBMISSION Papers should be submitted using SoftConf (https://www.softconf.com/emnlp2021/CRAC/) and should follow the EMNLP 2021 Style Files and Formatting guidelines (https://2021.emnlp.org/call-for-papers/style-and-formatting).
SHARED TASK A Shared Task on Anaphora Resolution in Dialogues (https://competitions.codalab.org/competitions/30312) is jointly run through CRAC 2021 and CODI 2021 (https://codi-workshop.github.io/) at EMNLP 2021.
ORGANIZING COMMITTEE ● Maciej Ogrodniczuk, Institute of Computer Science, Polish Academy of Sciences ● Sameer Pradhan, University of Pennsylvania and cemantix ● Yulia Grishina, Amazon ● Vincent Ng, University of Texas at Dallas ● Massimo Poesio, Queen Mary University of London