Improving Machine Learning Approaches to Coreference Resolution

Vincent Ng and Claire Cardie.
Proceedings of the 40th Anniversary Meeting of the Association for Computational Linguistics (ACL), pp. 104-111, 2002.

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

Abstract

We present a noun phrase coreference system that extends the work of Soon et al. (2001) and, to our knowledge, produces the best results to date on the MUC-6 and MUC-7 coreference resolution data sets -- F-measures of 70.4 and 63.4, respectively. Improvements arise from two sources: extra-linguistic changes to the learning framework and a large-scale expansion of the feature set to include more sophisticated linguistic knowledge.

BibTeX entry

@InProceedings{Ng+Cardie:02a,
  author = {Vincent Ng and Claire Cardie},
  title = {Improving Machine Learning Approaches to Coreference Resolution},
  booktitle = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics},
  pages = {104--111},
  year = 2002
}