MRD-based word sense disambiguation : further extending lesk

MRD-based word sense disambiguation : further extending lesk

This paper reconsiders the task of MRD-based word sense disambiguation, in extending the basic Lesk algorithm to investigate the impact on WSD performance of different tokenisation schemes, scoring mechanisms, methods of gloss extension and filtering methods. In experimentation over the Lexeed...

Full description

Saved in:
Bibliographic Details
Main Authors: Baldwin, Timothy, Su, Nam Kim, Bond, Francis, Fujita, Sanae, Martinez, David, Tanaka, Takaaki
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/10356/92271
http://hdl.handle.net/10220/6447
http://aclweb.org/mirror/ijcnlp08/program.htm
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:This paper reconsiders the task of MRD-based word sense disambiguation, in extending the basic Lesk algorithm to investigate the impact on WSD performance of different tokenisation schemes, scoring mechanisms, methods of gloss extension and filtering methods. In experimentation over the Lexeed Sensebank and the Japanese Senseval-2 dictionary task, we demonstrate that character bigrams with sense-sensitive gloss extension over hyponyms and hypernyms enhances WSD performance.

Similar Items