NP Animacy Identification for Anaphora Resolution

TL;DR

This paper explores two methods for identifying animacy in noun phrases to improve English anaphora resolution, demonstrating that machine learning approaches can achieve human-level performance and enhance resolution accuracy.

Contribution

It introduces and evaluates two novel animacy identification methods, including a machine learning approach that leverages WordNet with animacy info, improving anaphora resolution.

Findings

Machine learning method reaches human-level performance in animacy identification.

Animacy identification improves anaphora resolution accuracy.

High precision in identifying animate entities benefits resolution systems.

Abstract

In anaphora resolution for English, animacy identification can play an integral role in the application of agreement restrictions between pronouns and candidates, and as a result, can improve the accuracy of anaphora resolution systems. In this paper, two methods for animacy identification are proposed and evaluated using intrinsic and extrinsic measures. The first method is a rule-based one which uses information about the unique beginners in WordNet to classify NPs on the basis of their animacy. The second method relies on a machine learning algorithm which exploits a WordNet enriched with animacy information for each sense. The effect of word sense disambiguation on the two methods is also assessed. The intrinsic evaluation reveals that the machine learning method reaches human levels of performance. The extrinsic evaluation demonstrates that animacy identification can be beneficial in anaphora resolution, especially in the cases where animate entities are identified with high precision.