Paper: Learning Noun Phrase Anaphoricity To Improve Conference Resolution: Issues In Representation And Optimization

ACL ID P04-1020
Title Learning Noun Phrase Anaphoricity To Improve Conference Resolution: Issues In Representation And Optimization
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2004
Authors

Knowledge of the anaphoricity of a noun phrase might be profitably exploited by a coreference sys- tem to bypass the resolution of non-anaphoric noun phrases. Perhaps surprisingly, recent attempts to incorporate automatically acquired anaphoricity in- formation into coreference systems, however, have led to the degradation in resolution performance. This paper examines several key issues in com- puting and using anaphoricity information to im- prove learning-based coreference systems. In par- ticular, we present a new corpus-based approach to anaphoricity determination. Experiments on three standard coreference data sets demonstrate the ef- fectiveness of our approach.