Presentation 2006-07-27
Heteronym disambiguation based on co-occurrence within Web page
Eiichiro Sumita, Fumiaki Sugaya,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The authors claim that information around a word on the Web is useful for solving ambiguity related to the word. The proposed method learns a classifier based on the information. Appling the method to heteronym disambiguation demonstrated a high accuracy. Furthermore, it was effective for acronym disambiguation. However, when distribution of training data and that on the Web are largely different, we observed degradation, which is one of future works to be tackled.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Heteronym / Pronunciation / Acronym / Word Sense Disambiguation / Speech Processing / Web-based NLP
Paper # NLC2006-3
Date of Issue

Conference Information
Committee NLC
Conference Date 2006/7/20(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Vice Chair

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) Heteronym disambiguation based on co-occurrence within Web page
Sub Title (in English)
Keyword(1) Heteronym
Keyword(2) Pronunciation
Keyword(3) Acronym
Keyword(4) Word Sense Disambiguation
Keyword(5) Speech Processing
Keyword(6) Web-based NLP
1st Author's Name Eiichiro Sumita
1st Author's Affiliation NiCT & ATR()
2nd Author's Name Fumiaki Sugaya
2nd Author's Affiliation KDDI R&D Labs
Date 2006-07-27
Paper # NLC2006-3
Volume (vol) vol.106
Number (no) 190
Page pp.pp.-
#Pages 6
Date of Issue