Paper: Unsupervised Learning Of Contextual Role Knowledge For Coreference Resolution

ACL ID N04-1038
Title Unsupervised Learning Of Contextual Role Knowledge For Coreference Resolution
Venue Human Language Technologies
Session Main Conference
Year 2004
Authors

We present a coreference resolver called BABAR that uses contextual role knowledge to evaluate possible antecedents for an anaphor. BABAR uses information extraction patterns to identify contextual roles and creates four contextual role knowledge sources using unsu- pervised learning. These knowledge sources determine whether the contexts surrounding an anaphor and antecedent are compatible. BABAR applies a Dempster-Shafer probabilis- tic model to make resolutions based on ev- idence from the contextual role knowledge sources as well as general knowledge sources. Experiments in two domains showed that the contextual role knowledge improved corefer- ence performance, especially on pronouns.