Corpus-Based Learning for Noun Phrase Coreference Resolution

Abstract

In this paper, we present a learning approach for coreference resolution of noun phrases in unrestricted text. The approach learns from a small, annotated corpus and the task includes resolving not just pronouns but rather general noun phrases. In contrast to previous work, we attempt to evaluate our approach on a common data set, the MUC-6 coreferencc cor- pus. We obtained encouraging results, indicat- ing that on the general noun phrase coreference task, the learning approach holds promise and achieves accuracy comparable to non-learning approaches.