Improving Machine Learning Approaches to Coreference Resolution
Vincent Ng and Claire Cardie.
40th Annual Meeting of the Asssociation for Computational Linguistics (ACL), 2002.
Click here for the
PostScript or PDF
version.
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.