Indirect Anaphora Resolution as Semantic Path Search (2005)
Anaphora occur commonly in natural language text, and resolving them is essential for capturing the knowledge encoded in text. Indirect anaphora are especially challenging to resolve because the referring expression and the antecedent are related by unstated background knowledge. Such anaphora need to be resolved properly in order to automatically capture the knowledge expressed in natural language. Resolving indirect anaphora has been treated as a unique problem that requires special-purpose methods, and these methods have had limited success in precision and recall. In this study, we used a generic tool for finding semantic paths between two concepts to resolve these anaphora, and it achieved approximately twice the recall of the best previous system without loss of precision. A series of ablation study showed that the biggest increase in recall came from an abductive stopping criterion of the search.
In Proceedings of Third International Conference on Knowledge Capture 2005.

Ken Barker Formerly affiliated Research Scientist kbarker [at] cs utexas edu
James Jumin Fan Ph.D. Alumni jfan [at] cs utexas edu
Bruce Porter Faculty porter [at] cs utexas edu