Paper: A Twin-Candidate Model of Coreference Resolution with Non-Anaphor Identification Capability

ACL ID I05-1063
Title A Twin-Candidate Model of Coreference Resolution with Non-Anaphor Identification Capability
Venue International Joint Conference on Natural Language Processing
Session Main Conference
Year 2005
Authors
  • Xiaofeng Yang (Institute for Infocomm Research, Singapore; National University of Singapore, Singapore)
  • Jian Su (Institute for Infocomm Research, Singapore)
  • Chew Lim Tan (National University of Singapore, Singapore)

Although effective for antecedent determination, the tradi- tional twin-candidate model can not prevent the invalid resolution of non-anaphors without additional measures. In this paper we propose a modified learning framework for the twin-candidate model. In the new framework, we make use of non-anaphors to create a special class of training instances, which leads to a classifier capable of identifying the cases of non-anaphors during resolution. In this way, the twin-candidate model itself could avoid the resolution of non-anaphors, and thus could be directly deployed to coreference resolution. The evaluation done on newswire domain shows that the twin-candidate based system with our modified framework achieves better and more reliable performance than those with other solutions.