Presentation 2011/12/12
Evaluation of Lexicon Optimization based on Discriminative Learning
Mijit Ablimit, Tatsuya Kawahara, Askar Hamdulla,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In agglutinative languages, selection of lexical unit is not obvious. Morpheme unit is usually adopted to ensure a sufficient coverage, but many morphemes are short, resulting in weak constraints and possible confusions. In this paper, we propose a discriminative approach to select lexical entries which will directly contribute to ASR error reduction. We define an evaluation function for each word by a set of features and their weights, and the measure for optimization by the difference of WERs by the morpheme-based model and by the word-based model. Then, the weights of the features are learned by a perceptron algorithm. Finally, word (or sub-word) entries with higher evaluation scores are selected to be added to the lexicon. This method is successfully applied to an Uyghur large-vocabulary continuous speech recognition system, resulting in a significant reduction of WER and the lexicon size. Further improvement is achieved by combining with a statistical method based on mutual information criterion.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper # Vol.2011-SLP-89 No.2
Date of Issue

Conference Information
Committee NLC
Conference Date 2011/12/12(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Evaluation of Lexicon Optimization based on Discriminative Learning
Sub Title (in English)
Keyword(1)
1st Author's Name Mijit Ablimit
1st Author's Affiliation School of Informatics, Kyoto University:Institute of Information Engineering, Xinjiang University()
2nd Author's Name Tatsuya Kawahara
2nd Author's Affiliation School of Informatics, Kyoto University
3rd Author's Name Askar Hamdulla
3rd Author's Affiliation Institute of Information Engineering, Xinjiang University
Date 2011/12/12
Paper # Vol.2011-SLP-89 No.2
Volume (vol) vol.111
Number (no) 364
Page pp.pp.-
#Pages 5
Date of Issue