Presentation	2001/10/10 Ibaraki: learning system of WSD rules developed for SENSEVAL2 Japanese translation task Hiroyuki SHINNOU,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	We made a learning system of word sense disambiguation rules, named Ibaraki, for SENSEVAL2 Japanese translation task. First, we estimated that an unsupervised learning method is efficient for this task, and planed to use it. However, we gave up using the method. As a result, our system was ended up a simple learning system using the decision list method. In this paper, we report why we estimate that an unsupervised learning method is efficient for this task, and why we gave up it. Moreover, we also evaluate our system made as a result. After the contest, we integrated an unsupervised learning technique into Ibaraki. We report about it briefly.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	SENSEVAL2 / Translation Task / Unsupervised learning / Decision list
Paper #	NLC 2001-39
Date of Issue

Conference Information
Committee	NLC
Conference Date	2001/10/10(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Natural Language Understanding and Models of Communication (NLC)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Ibaraki: learning system of WSD rules developed for SENSEVAL2 Japanese translation task
Sub Title (in English)
Keyword(1)	SENSEVAL2
Keyword(2)	Translation Task
Keyword(3)	Unsupervised learning
Keyword(4)	Decision list
1st Author's Name	Hiroyuki SHINNOU
1st Author's Affiliation	Faculty of Engineering, Ibaraki University()
Date	2001/10/10
Paper #	NLC 2001-39
Volume (vol)	vol.101
Number (no)	351
Page	pp.pp.-
#Pages	6
Date of Issue