Learning Anaphoricity and Antecedent Ranking Features for Coreference Resolution
MetadataShow full item record
CitationWiseman, Sam, Alexander M. Rush, Stuart M. Shieber, and Jason Weston. 2015. Learning Anaphoricity and Antecedent Ranking Features for Coreference Resolution. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics (ACL-IJCNLP 2015), Beijing, China, July 26-31, 2016, 1416-1426.
AbstractWe introduce a simple, non-linear mention-ranking model for coreference resolution that attempts to learn distinct feature representations for anaphoricity detection and antecedent ranking, which we encourage by pre-training on a pair of corresponding subtasks. Although we use only simple, unconjoined features, the model is able to learn useful representations, and we report the best overall score on the CoNLL 2012 English test set to date.
Citable link to this pagehttp://nrs.harvard.edu/urn-3:HUL.InstRepos:24830901
- FAS Scholarly Articles