Presentation 2000/1/21
Linkgram Language Modeling
Shuwu Zhang, Hirofumi Yamamoto, Yoshinori Sagisaka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a linkgram language modeling approach to exploit longer distance linguistic correlations between units. Based on the annotated language corpus, we can extract some syntactic link dependencies between longer history units. In order to integrate these linguistic constraints effectively, we further simplify the link features as syntactic trigger pairs by pruning some unnecessary attributes. Then, the exponential parameters of the link features can be estimated binding with a previous proposed DUAME model by maximum entropy approach. Experimental results showed that linkgram modeling is very useful in complementing underlying language modeling.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Linkgram / Link Features / Maximum Entropy / Language Modeling
Paper # SP99-144
Date of Issue

Conference Information
Committee SP
Conference Date 2000/1/21(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 Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Linkgram Language Modeling
Sub Title (in English)
Keyword(1) Linkgram
Keyword(2) Link Features
Keyword(3) Maximum Entropy
Keyword(4) Language Modeling
1st Author's Name Shuwu Zhang
1st Author's Affiliation ATR Interpeting Telecommunication Research Labs.()
2nd Author's Name Hirofumi Yamamoto
2nd Author's Affiliation ATR Interpeting Telecommunication Research Labs.
3rd Author's Name Yoshinori Sagisaka
3rd Author's Affiliation ATR Interpeting Telecommunication Research Labs.
Date 2000/1/21
Paper # SP99-144
Volume (vol) vol.99
Number (no) 577
Page pp.pp.-
#Pages 6
Date of Issue