mirage

Word sense disambiguation incorporating lexical and structural semantic information.

DSpace/Manakin Repository

 

Search DR-NTU


Advanced Search Subject Search

Browse

My Account

Word sense disambiguation incorporating lexical and structural semantic information.

Show full item record

Title: Word sense disambiguation incorporating lexical and structural semantic information.
Author: Tanaka, Takaaki.; Bond, Francis.; Baldwin, Timothy.; Fujita, Sanae.; Hashimoto, Chikara.
Copyright year: 2007
Abstract: 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.
Subject: DRNTU::Humanities::Language::Japanese.DRNTU::Humanities::Linguistics::Sociolinguistics::Computational linguistics.
Type: Conference Paper
Conference name: Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (2007 : Prague)
School: School of Humanities and Social Sciences
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].
Version: Accepted version

Files in this item

Files Size Format View
D07-1050.pdf 226.6Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record

Statistics

Total views

All Items Views
Word sense disambiguation incorporating lexical and structural semantic information. 292

Total downloads

All Bitstreams Views
D07-1050.pdf 140

Top country downloads

Country Code Views
United States of America 50
Singapore 22
China 16
Russian Federation 9
Unknown Country 7

Top city downloads

city Views
Mountain View 40
Singapore 22
Tehran 4
San Jose 2
Seattle 2

Downloads / month

  2014-05 2014-06 2014-07 total
D07-1050.pdf 0 0 7 7