Word sense disambiguation incorporating lexical and structural semantic information

We 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...

Full description

Saved in:

Bibliographic Details
Main Authors:	Tanaka, Takaaki, Bond, Francis, Baldwin, Timothy, Fujita, Sanae, Hashimoto, Chikara
Other Authors:	School of Humanities and Social Sciences
Format:	Conference or Workshop Item
Language:	English
Published:	2010
Subjects:	DRNTU::Humanities::Language::Japanese DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics
Online Access:	https://hdl.handle.net/10356/92286 http://hdl.handle.net/10220/6449
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-92286
record_format	dspace
spelling	sg-ntu-dr.10356-922862019-12-06T18:20:42Z Word sense disambiguation incorporating lexical and structural semantic information Tanaka, Takaaki Bond, Francis Baldwin, Timothy Fujita, Sanae Hashimoto, Chikara School of Humanities and Social Sciences Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (2007 : Prague) DRNTU::Humanities::Language::Japanese DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics We 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. Accepted version 2010-10-26T09:25:25Z 2019-12-06T18:20:42Z 2010-10-26T09:25:25Z 2019-12-06T18:20:42Z 2007 2007 Conference Paper Tanaka, 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) https://hdl.handle.net/10356/92286 http://hdl.handle.net/10220/6449 155517 en © 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]. 10 p. application/pdf
institution	Nanyang Technological University
building	NTU Library
country	Singapore
collection	DR-NTU
language	English
topic	DRNTU::Humanities::Language::Japanese DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics
spellingShingle	DRNTU::Humanities::Language::Japanese DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics Tanaka, Takaaki Bond, Francis Baldwin, Timothy Fujita, Sanae Hashimoto, Chikara Word sense disambiguation incorporating lexical and structural semantic information
description	We 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.
author2	School of Humanities and Social Sciences
author_facet	School of Humanities and Social Sciences Tanaka, Takaaki Bond, Francis Baldwin, Timothy Fujita, Sanae Hashimoto, Chikara
format	Conference or Workshop Item
author	Tanaka, Takaaki Bond, Francis Baldwin, Timothy Fujita, Sanae Hashimoto, Chikara
author_sort	Tanaka, Takaaki
title	Word sense disambiguation incorporating lexical and structural semantic information
title_short	Word sense disambiguation incorporating lexical and structural semantic information
title_full	Word sense disambiguation incorporating lexical and structural semantic information
title_fullStr	Word sense disambiguation incorporating lexical and structural semantic information
title_full_unstemmed	Word sense disambiguation incorporating lexical and structural semantic information
title_sort	word sense disambiguation incorporating lexical and structural semantic information
publishDate	2010
url	https://hdl.handle.net/10356/92286 http://hdl.handle.net/10220/6449
_version_	1681043308225232896

Word sense disambiguation incorporating lexical and structural semantic information

Similar Items