Presentation 2006/12/14
System Request Discrimination Based on AdaBoost
Atsushi SAKO, Tetsuya TAKIGUCHI, Yasuo ARIKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is difficult to discriminate a request to a system from a chat based on only simple keywords, because keywords are sometime included in utterances of explaining an usage of a system, or appear by misrecognition in chats. On another front, it has troubles to use network grammar, bacause it makes the usage difficult for people unaccustomed to a system due to fixed expressions of system request. In this paper, we propose a discrimination method based on AdaBoost using linguistic information obtained from speech recognition. To solve a problem of misrecognition, a confution network is employed. The confusion network permits deep hypothesises of speech recognition. The experimental results showed that 95.7% of precision and 89.8% of recall on a task which is recognized with 42.1% of word accuracy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) AdaBoost / System Request Discrimination / Support Vector Machine / Speech Recognition
Paper # NLC2006-32,SP2006-88
Date of Issue

Conference Information
Committee NLC
Conference Date 2006/12/14(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 JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) System Request Discrimination Based on AdaBoost
Sub Title (in English)
Keyword(1) AdaBoost
Keyword(2) System Request Discrimination
Keyword(3) Support Vector Machine
Keyword(4) Speech Recognition
1st Author's Name Atsushi SAKO
1st Author's Affiliation Guraduate School of Science and Technology, Kobe University()
2nd Author's Name Tetsuya TAKIGUCHI
2nd Author's Affiliation Faculty of Engineering, Kobe University
3rd Author's Name Yasuo ARIKI
3rd Author's Affiliation Faculty of Engineering, Kobe University
Date 2006/12/14
Paper # NLC2006-32,SP2006-88
Volume (vol) vol.106
Number (no) 441
Page pp.pp.-
#Pages 6
Date of Issue