Abstract
There is a significant gap between the performance of a coreference resolution system on gold mentions and on system mentions. This gap is due to the large and unbalanced search space in coreference resolution when using system mentions. In this paper we show that search space pruning is a simple but efficient way of improving coreference resolvers. By incorporating our pruning method in one of the state-of-the-art coreference resolution systems, we achieve the best reported overall score on the CoNLL 2012 English test set. A version of our pruning method is available with the Cort coreference resolution source code.
Cite
CITATION STYLE
Moosavi, N. S., & Strube, M. (2016). Search space pruning: A simple solution for better coreference resolvers. In 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference (pp. 1005–1011). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/n16-1115
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.