dc.contributor.authorTanaka, Takaaki
dc.contributor.authorBond, Francis
dc.contributor.authorBaldwin, Timothy
dc.contributor.authorFujita, Sanae
dc.contributor.authorHashimoto, Chikara
dc.date.accessioned2010-10-26T09:25:25Z
dc.date.available2010-10-26T09:25:25Z
dc.date.copyright2007en_US
dc.date.issued2007
dc.identifier.citationTanaka, T., Bond, F., Baldwin, T., Fujita, S., & Hashimoto, C. (2007). Word sense disambiguation incorporating lexical and structural semantic information. Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)
dc.identifier.urihttp://hdl.handle.net/10220/6449
dc.description.abstractWe present results that show that incorporating lexical and structural semantic information is effective for word sense disambiguation. We evaluated the method by using precise information from a large treebank and an ontology automatically created from dictionary sentences. Exploiting rich semantic and structural information improves precision 2–3%. The most gains are seen with verbs, with an improvement of 5.7% over a model using only bag of words and n-gram features.en_US
dc.format.extent10 p.en_US
dc.language.isoenen_US
dc.rights© 2007 ACL This is the author created version of a work that has been peer reviewed and accepted for publication by Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), Association for Computational Linguistics. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [URL: http://www.aclweb.org/anthology-new/D/D07/D07-1050.pdf].
dc.subjectDRNTU::Humanities::Language::Japanese
dc.subjectDRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics
dc.titleWord sense disambiguation incorporating lexical and structural semantic informationen_US
dc.typeConference Paper
dc.contributor.conferenceJoint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (2007 : Prague)en_US
dc.contributor.schoolSchool of Humanities and Social Sciencesen_US
dc.description.versionAccepted versionen_US
dc.identifier.rims155517


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record