Presentation 1997/12/12
Grammar Fragment Acquisition using Syntactic and Semantic Clustering
Kazuhiro Arai, Jeremy H. Wight, Giuseppe Riccardi, Allen L. Gorin,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A new method for automatically acquiring grammar fragments for understanding fluently spoken language is proposed. The goal of this method is to generate a collection of grammar fragments each representing a set of syntactically and semantically similar phrases. First phrases observed frequently in the training set are selected as candidates. Each candidate phrase has three associated probability distributions: of succeeding contexts, of preceding contexts, and of associated machine actions. The similarity between candidate phrases is measured by applying the Kullback-Leibler distance to three probability distributions. Candidate phrases which are close in all three distances are clustered into a grammar fragment. This approach detected 246 phrases in the test-set that were not present in the training-set. Experimental results show that a 3% improvement in the call-type classification performance has been achieved by introducing these fragments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) spoken understanding / preceding and succeeding contexts / Kullback-Leibler distance / phrase similarity / phrase clustering
Paper # NLC97-51
Date of Issue

Conference Information
Committee NLC
Conference Date 1997/12/12(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Grammar Fragment Acquisition using Syntactic and Semantic Clustering
Sub Title (in English)
Keyword(1) spoken understanding
Keyword(2) preceding and succeeding contexts
Keyword(3) Kullback-Leibler distance
Keyword(4) phrase similarity
Keyword(5) phrase clustering
1st Author's Name Kazuhiro Arai
1st Author's Affiliation NTT Human Interface Laboratories()
2nd Author's Name Jeremy H. Wight
2nd Author's Affiliation AT&T Laboratories-Research
3rd Author's Name Giuseppe Riccardi
3rd Author's Affiliation AT&T Laboratories-Research
4th Author's Name Allen L. Gorin
4th Author's Affiliation AT&T Laboratories-Research
Date 1997/12/12
Paper # NLC97-51
Volume (vol) vol.97
Number (no) 440
Page pp.pp.-
#Pages 8
Date of Issue