Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
An algorithm for pronominal anaphora resolution
Computational Linguistics
Machine Learning
Multilingual Anaphora Resolution
Machine Translation
Improving machine learning approaches to coreference resolution
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
A machine learning approach to pronoun resolution in spoken dialogue
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Comparing Knowledge Sources for Nominal Anaphora Resolution
Computational Linguistics
Using the web in machine learning for other-anaphora resolution
EMNLP '03 Proceedings of the 2003 conference on Empirical methods in natural language processing
Machine learning for coreference resolution: from local classification to global ranking
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Bootstrapping path-based pronoun resolution
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Kernel-based pronoun resolution with structured syntactic knowledge
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Hi-index | 0.00 |
Pronominal anaphors are commonly observed in written texts. Inthis article, effective Chinese pronominal anaphora resolution isaddressed by using lexical knowledge acquisition and saliencemeasurement. The lexical knowledge acquisition is aimed to extractmore semantic features, such as gender, number, and collocatecompatibility by employing multiple resources. The presentedsalience measurement is based on entropy-based weighting onselecting antecedent candidates. The resolution is justified with areal corpus and compared with a rule-based model. Experimentalresults by five-fold cross-validation show that our approach yields82.5% success rate on 1343 anaphoric instances. In comparison witha general rule-based approach, the performance is improved by 7%.© 2008 Wiley Periodicals, Inc.