The last five years have seen a dramatic improvement in the ability of NLP systems to understand and produce words and sentences. This development has created a renewed interest in discourse problems as researchers move towards the processing of long-form text and conversations. There is a surge of activity in discourse parsing, coherence models, text summarization, corpora for discourse level reading comprehension, and discourse related/aided representation learning, to name a few. At this juncture, we organize the 1st Workshop on Computational Approaches to Discourse (CODI) to be held at EMNLP 2020 to bring together discourse experts and upcoming researchers. This workshop will catalyze the speed and knowledge needed to solve such problems and serve as a forum for the discussion of suitable datasets and reliable evaluation methods.
The previous workshops on discourse in machine translation (DiscoMT), linking lexical, sentential and discourse semantics (LSDSem), discourse structure in natural language generation (DSNNLG), discourse parsing and treebanking (DisRPT) and coreference (CORBON/CRAC), have shown that there is considerable interest and success in bringing together the community working on specific problems. We believe that the discourse community will also benefit from a general forum where work ranging from corpus development/analysis to computational models, and evaluation is discussed, and desiderata can be drawn for future progress.
The 2nd CODI workshop is planned as a 2 day event which brings together different subcommunities. It will feature invited talks and regular papers on the first day. The second day will be dedicated to shared tasks and special sessions which focus on the specific issues mentioned above, with already one planned on discourse representations and treebanking, the focus of the DisRPT workshop, and another one on coreference. The shared tasks will include a coreference resolution task (encompassing entity and abstract coreference and bridging anaphora) in text and dialogue (organized by Sopan Kosla, Ramesh Manuvinakurike, Massimo Poesio, Carolyn Rose, Michael Strube) and a discourse parsing task (second DisRPT shared task, organized by Chloé Braud, Mikel Iruskieta, Philippe Muller and Amir Zeldes).
The workshop will take place during EMNLP 2021, thus in November 10-11, 2021.
18 May, 2021: 1st Call for Workshop Papers
5 July, 2021: Anonymity period starts
5 August, 12 August, 2021: Workshop Papers Due (long, short, demo, extended abstracts)
5 September, 23 September, 2021: Notification of Acceptance
15 September, 28 September, 2021: Camera-ready papers due
10-11 November, 2021: Workshop Date
All deadlines are 11.59 pm UTC -12h (“anywhere on Earth”).
Please submit your paper on: https://www.softconf.com/emnlp2021/CODI/.
To contact the organizers, please send an email to: codi-workshop@googlegroups.com