CRAC 2019 was the Second Workshop on Computational Models of Reference, Anaphora and Coreference, held on June 7 at NAACL 2019. Thank you for joining in!
Background: The end of Discourse Anaphora and Anaphor Resolution Colloquium series in 2011 scattered the research papers on anaphora/coreference resolution among very different fora until a common event in Computational Linguistics entirely dedicated to this area was revived in 2016 with the Coreference Beyond OntoNotes (CORBON 2016) workshop co-located with NAACL and CORBON 2017 co-located with EACL. In 2018 its focus, perceived as too narrow, was broadened to cover all cases of computational modelling of reference, anaphora, and coreference with CRAC 2018 workshop held again at NAACL. Following the recent advances in application of word embeddings and deep neural networks to various NLP tasks, we believe that the task of cross-lingual coreference resolution can also benefit from the new perspective.
Objectives: The aim of the workshop was 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 welcomed submissions describing both theoretical and applied computational work on anaphora/coreference resolution, including on languages other than English, and less-researched types of anaphora such as bridging references.
Topics of interest included the following:
09:00–09:15: Welcome
09:15–10:30: Invited talk
Amir Zeldes (Georgetown University)
Coreference and coherence revisited
10:30–11:00: Coffee break
11:00–11:30:
Oshin Agarwal, Sanjay Subramanian, Ani Nenkova and Dan Roth
Evaluation of Named Entity Coreference
11:30–12:00:
Loïc Grobol
12:00–12:30:
Jenny Kunz and Christian Hardmeier
Entity Decisions in Neural Language Modelling: Approaches and Problems
12:30–14:00: Lunch break
14:00–14:30:
Kevin Blissett and Heng Ji
Cross-lingual NIL Entity Clustering for Low-resource Languages
14:30–15:00:
Ekaterina Lapshinova-Koltunski, Sharid Loáiciga, Christian Hardmeier and Pauline Krielke
Cross-lingual Incongruences in the Annotation of Coreference
15:00–15:30:
Gorka Urbizu, Ander Soraluze and Olatz Arregi
Deep Cross-Lingual Coreference Resolution for Less-Resourced Languages: The Case of Basque
15:30–16:00:
Closing of the workshop
The workshop received 10 submissions: half of them were from Europe, two were from the U.S., and the remaining three were from India. We were pleased to see that the submissions covered not only a variety of less-studied languages in the coreference community (e.g., Basque, French, German, Malayalam or Tamil) but also many under-investigated topics in coreference resolution (e.g., feature representation, coreference for low-resource languages, coreference in specialized domains, and evaluation of coreference resolvers).
While it is perhaps not surprising to receive submissions focusing on the design and use of neural models for coreference resolution given the recent popularity of deep learning for natural language processing, it is interesting to see that the most popular topic among the submitted papers is cross-lingual coreference resolution. In fact, one of the workshop sessions was devoted entirely to this topic.
Workshop proceedings are available at the ACL Anthology.