1998 AStatisticalApproachToAnaphoraResolution

From GM-RKB
Jump to navigation Jump to search

Subject Headings: Supervised Anaphora Resolution Algorithm.

Notes

Cited By

2001

Quotes

Abstract

This paper presents an algorithm for identifying pronominal anaphora and two experiments based upon this algorithm. We incorporate multiple anaphora resolution factors into a statistical framework -- specifically the distance between the pronoun and the proposed antecedent, gender/number/animaticity of the proposed antecedent, governing head information and noun phrase repetition. We combine them into a single probability that enables hs to identify the referent. Our first experiment shows the relative contribution of each source Of information and demonstrates a success rate of 82.9% for all sources combined. The second experiment investigates a method for unsuper- vised learning of gender/number/animaticity information. We present some experiments illustrating the accuracy of the method and note that with this information added, our pronoun resolution method achieves 84.2% accuracy.


,

 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
1998 AStatisticalApproachToAnaphoraResolutionEugene Charniak
Niyu Ge
John Hale
A Statistical Approach to Anaphora Resolutionhttp://acl.ldc.upenn.edu/W/W98/W98-1119.pdf