A machine learning approach to coreference resolution of noun phrases
Computational Linguistics - Special issue on computational anaphora resolution
Evaluating automated and manual acquisition of anaphora resolution strategies
ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Fertilization of case frame dictionary for robust Japanese case analysis
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Pronoun resolution in Japanese sentences using surface expressions and examples
CorefApp '99 Proceedings of the Workshop on Coreference and its Applications
Using decision trees for conference resolution
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Improving Japanese zero pronoun resolution by global word sense disambiguation
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Automatic construction of nominal case frames and its application to indirect anaphora resolution
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
COLING-ACL '06 Proceedings of the COLING/ACL on Main conference poster sessions
CSCL utterance NLP analysis and inter-LMS sharing with use of Web Services
International Journal of Advanced Intelligence Paradigms
Text understanding for conversational agent
IMTCI'04 Proceedings of the Second international conference on Intelligent Media Technology for Communicative Intelligence
Hi-index | 0.00 |
This paper describes a method to detect and resolve zero pronouns in Japanese text. We detect zero pronouns by case analysis based on automatically constructed case frames, and select their appropriate antecedents based on similarity to examples in the case frames. We also introduce structural preference of antecedents to precisely capture the tendency that a zero pronoun has its antecedent in its close position. Experimental results on 100 articles indicated that the precision and recall of zero pronoun detection is 87.1% and 74.8% respectively and the accuracy of antecedent estimation is 61.8%.