Paper: Resolving And Generating Definite Anaphora By Modeling Hypernymy Using Unlabeled Corpora

ACL ID W06-2906
Title Resolving And Generating Definite Anaphora By Modeling Hypernymy Using Unlabeled Corpora
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2006
Authors

We demonstrate an original and success- ful approach for both resolving and gen- erating definite anaphora. We propose and evaluate unsupervised models for ex- tracting hypernym relations by mining co- occurrence data of definite NPs and po- tential antecedents in an unlabeled cor- pus. The algorithm outperforms a stan- dard WordNet-based approach to resolv- ing and generating definite anaphora. It also substantially outperforms recent re- lated work using pattern-based extraction of such hypernym relations for corefer- ence resolution.