Presentation	2006-05-18 A method for detecting semantic diversity of words across large-scale text corpora AKIKO AIZAWA,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	This paper focuses on issues in automatic extraction of synonyms from large scale untagged corpora. In the paper, a coocurrence analysis-based method is first introduced where synonyms and sample phrases are extracted simultaneously utilizing the result of word dependency analysis. Next, the influence of the corpus scale to the extraction result is examined using newspaper collections. A demonstrative example of the extracted dictionary is also shown.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	text corpora / automatic construction of synonymous words dictionaries / cooccurrencies of words / text mining
Paper #	AI2006-11
Date of Issue

Conference Information
Committee	AI
Conference Date	2006/5/11(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	Artificial Intelligence and Knowledge-Based Processing (AI)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	A method for detecting semantic diversity of words across large-scale text corpora
Sub Title (in English)
Keyword(1)	text corpora
Keyword(2)	automatic construction of synonymous words dictionaries
Keyword(3)	cooccurrencies of words
Keyword(4)	text mining
1st Author's Name	AKIKO AIZAWA
1st Author's Affiliation	National Institute of Informatics:Graduate School for Advanced Studies()
Date	2006-05-18
Paper #	AI2006-11
Volume (vol)	vol.106
Number (no)	38
Page	pp.pp.-
#Pages	6
Date of Issue