Enforcing Transitivity in Coreference Resolution

Abstract

A desirable quality of a coreference resolution system is the ability to handle transitivity constraints, such that even if it places high likelihood on a particular mention being coreferent with each of two other mentions, it will also consider the likelihood of those two mentions being coreferent when making a final assignment. This is exactly the kind of constraint that integer linear programming (ILP) is ideal for, but, surprisingly, previous work applying ILP to coreference resolution has not encoded this type of constraint. We train a coreference classifier over pairs of mentions, and show how to encode this type of constraint on top of the probabilities output from our pairwise classifier to extract the most probable legal entity assignments. We present results on two commonly used datasets which show that enforcement of transitive closure consistently improves performance, including improvements of up to 3.6% using the b scorer, and up to 16.5% using cluster f-measure.

Extracted Key Phrases

1 Figure or Table

Statistics

01020200920102011201220132014201520162017
Citations per Year

89 Citations

Semantic Scholar estimates that this publication has 89 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Finkel2008EnforcingTI, title={Enforcing Transitivity in Coreference Resolution}, author={Jenny Rose Finkel and Christopher D. Manning}, booktitle={ACL}, year={2008} }