A Machine Learning Approach to Coreference Resolution of Noun Phrases

TLDR

The study proposes a learning-based method for resolving coreference of noun phrases in unrestricted text. The method learns from a small annotated corpus to resolve coreference of general noun phrases across entity types and is evaluated on the MUC‑6 and MUC‑7 corpora, achieving accuracy comparable to nonlearning approaches. On MUC‑6 and MUC‑7, the system attains accuracy comparable to state‑of‑the‑art nonlearning systems, making it the first learning-based approach to reach such performance.

Abstract

In this paper, we present a learning approach to coreference resolution of noun phrases in unrestricted text. The approach learns from a small, annotated corpus and the task includes resolving not just a certain type of noun phrase (e.g., pronouns) but rather general noun phrases. It also does not restrict the entity types of the noun phrases; that is, coreference is assigned whether they are of “organization,” “person,” or other types. We evaluate our approach on common data sets (namely, the MUC-6 and MUC-7 coreference corpora) and obtain encouraging results, indicating that on the general noun phrase coreference task, the learning approach holds promise and achieves accuracy comparable to that of nonlearning approaches. Our system is the first learning-based system that offers performance comparable to that of state-of-the-art nonlearning systems on these data sets.