Learning Noun Phrase Anaphoricity to Improve Coreference Resolution: Issues in Representation and Optimization

Vincent Ng.
Proceedings of the 42nd Annual Meeting of the Asssociation for Computational Linguistics (ACL), pp. 152-159, 2004.

Click here for the PostScript or PDF version. The talk slides are available here.

Abstract

Knowledge of the anaphoricity of a noun phrase might be profitably exploited by a coreference system to bypass the resolution of non-anaphoric noun phrases. Perhaps surprisingly, recent attempts to incorporate automatically acquired anaphoricity information into coreference systems, however, have led to the degradation in resolution performance. This paper examines several key issues in computing and using anaphoricity information to improve learning-based coreference systems. In particular, we present a new corpus-based approach to anaphoricity determination. Experiments on three standard coreference data sets demonstrate the effectiveness of our approach.

BibTeX entry

@InProceedings{Ng:04a,
  author = {Vincent Ng},
  title = {Learning Noun Phrase Anaphoricity to Improve Coreference Resolution: Issues in Representation and Optimization},
  booktitle = {Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics},
  pages = {152--159},
  year = 2004
}