Presentation 2009/12/14
Estimation method of user satisfaction based on dialog history N-gram for spoken dialog system
Sunao Hara, Norihide Kitaoka, Kazuya Takeda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose an estimation method of user satisfaction for a spoken dialog system using an N-gram likelihood based on dialog history model. For the experiment, we use spoken dialog histories between users and the system, which is contained in an real environmental speech data that was collected by a music retrieval system with a spoken dialog interface, and we estimate their satisfaction level based on the N-gram likelihood. An N-gram model is trained from encoded sequences that consist of users' dialog acts and the system's dialog acts for each user satisfaction level. Experimental results show that our proposed method achieved good classification performance, especially the false detection rate of 10% in the experiment of a classification into dialogs with task completion and those without task completion.
Keyword(in Japanese) (See Japanese page)
Keyword(in English)
Paper #
Date of Issue

Conference Information
Committee NLC
Conference Date 2009/12/14(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) Estimation method of user satisfaction based on dialog history N-gram for spoken dialog system
Sub Title (in English)
Keyword(1)
1st Author's Name Sunao Hara
1st Author's Affiliation Graduate School of Information Science, Nagoya University()
2nd Author's Name Norihide Kitaoka
2nd Author's Affiliation Graduate School of Information Science, Nagoya University
3rd Author's Name Kazuya Takeda
3rd Author's Affiliation Graduate School of Information Science, Nagoya University
Date 2009/12/14
Paper #
Volume (vol) vol.109
Number (no) 355
Page pp.pp.-
#Pages 6
Date of Issue