Multi-lingual coreference resolution with syntactic features

Abstract

In this paper, we study the impact of a group of features extracted automatically from machine-generated parse trees on coreference resolution. One focus is on designing syntactic features using the binding theory as the guideline to improve pronoun resolution, although linguistic phenomenon such as apposition is also modeled. These features are applied to the Arabic, Chinese and English coreference resolution systems and their effectiveness is evaluated on data from the Automatic Content Extraction (ACE) task. The syntactic features improve the Arabic and English systems significantly, but play a limited role in the Chinese one. Detailed analyses are done to understand the syntactic features' impact on the three coreference systems. © 2005 Association for Computational Linguistics.