Detection of task-incomplete dialogs based on utterance-and-behavior tag N-gram for spoken dialog systems

Sunao Hara, Norihide Kitaoka, Kazuya Takeda

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

We propose a method of detecting "task incomplete" dialogs in spoken dialog systems using N-gram-based dialog models. We used a database created during a field test in which inexperienced users used a client-server music retrieval system with a spoken dialog interface on their own PCs. In this study, the dialog for a music retrieval task consisted of a sequence of user and system tags that related their utterances and behaviors. The dialogs were manually classified into two classes: the dialog either completed the music retrieval task or it didn't. We then detected dialogs that did not complete the task, using N-gram probability models or a Support Vector Machine with N-gram feature vectors trained using manually classified dialogs. Offline and on-line detection experiments were conducted on a large amount of real data, and the results show that our proposed method achieved good classification performance.

Original languageEnglish
Title of host publicationProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Pages1305-1308
Number of pages4
Publication statusPublished - 2011
Externally publishedYes
Event12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011 - Florence, Italy
Duration: Aug 27 2011Aug 31 2011

Other

Other12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011
CountryItaly
CityFlorence
Period8/27/118/31/11

Fingerprint

Spoken Dialogue Systems
N-gram
Computer music
Interfaces (computer)
Support vector machines
Computer systems
Servers
Music
Retrieval
Experiments
Dialogue
Utterance
Tag
Incomplete
Client/server
Probability Model
Feature Vector
Support Vector Machine

Keywords

  • Breakdowns in dialog
  • N-gram
  • Spoken dialog system
  • Task incomplete dialog detection

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Cite this

Hara, S., Kitaoka, N., & Takeda, K. (2011). Detection of task-incomplete dialogs based on utterance-and-behavior tag N-gram for spoken dialog systems. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (pp. 1305-1308)

Detection of task-incomplete dialogs based on utterance-and-behavior tag N-gram for spoken dialog systems. / Hara, Sunao; Kitaoka, Norihide; Takeda, Kazuya.

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2011. p. 1305-1308.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hara, S, Kitaoka, N & Takeda, K 2011, Detection of task-incomplete dialogs based on utterance-and-behavior tag N-gram for spoken dialog systems. in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 1305-1308, 12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011, Florence, Italy, 8/27/11.
Hara S, Kitaoka N, Takeda K. Detection of task-incomplete dialogs based on utterance-and-behavior tag N-gram for spoken dialog systems. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2011. p. 1305-1308
Hara, Sunao ; Kitaoka, Norihide ; Takeda, Kazuya. / Detection of task-incomplete dialogs based on utterance-and-behavior tag N-gram for spoken dialog systems. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2011. pp. 1305-1308
@inproceedings{da73de43d90c4f50bd019e245469dc44,
title = "Detection of task-incomplete dialogs based on utterance-and-behavior tag N-gram for spoken dialog systems",
abstract = "We propose a method of detecting {"}task incomplete{"} dialogs in spoken dialog systems using N-gram-based dialog models. We used a database created during a field test in which inexperienced users used a client-server music retrieval system with a spoken dialog interface on their own PCs. In this study, the dialog for a music retrieval task consisted of a sequence of user and system tags that related their utterances and behaviors. The dialogs were manually classified into two classes: the dialog either completed the music retrieval task or it didn't. We then detected dialogs that did not complete the task, using N-gram probability models or a Support Vector Machine with N-gram feature vectors trained using manually classified dialogs. Offline and on-line detection experiments were conducted on a large amount of real data, and the results show that our proposed method achieved good classification performance.",
keywords = "Breakdowns in dialog, N-gram, Spoken dialog system, Task incomplete dialog detection",
author = "Sunao Hara and Norihide Kitaoka and Kazuya Takeda",
year = "2011",
language = "English",
pages = "1305--1308",
booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

}

TY - GEN

T1 - Detection of task-incomplete dialogs based on utterance-and-behavior tag N-gram for spoken dialog systems

AU - Hara, Sunao

AU - Kitaoka, Norihide

AU - Takeda, Kazuya

PY - 2011

Y1 - 2011

N2 - We propose a method of detecting "task incomplete" dialogs in spoken dialog systems using N-gram-based dialog models. We used a database created during a field test in which inexperienced users used a client-server music retrieval system with a spoken dialog interface on their own PCs. In this study, the dialog for a music retrieval task consisted of a sequence of user and system tags that related their utterances and behaviors. The dialogs were manually classified into two classes: the dialog either completed the music retrieval task or it didn't. We then detected dialogs that did not complete the task, using N-gram probability models or a Support Vector Machine with N-gram feature vectors trained using manually classified dialogs. Offline and on-line detection experiments were conducted on a large amount of real data, and the results show that our proposed method achieved good classification performance.

AB - We propose a method of detecting "task incomplete" dialogs in spoken dialog systems using N-gram-based dialog models. We used a database created during a field test in which inexperienced users used a client-server music retrieval system with a spoken dialog interface on their own PCs. In this study, the dialog for a music retrieval task consisted of a sequence of user and system tags that related their utterances and behaviors. The dialogs were manually classified into two classes: the dialog either completed the music retrieval task or it didn't. We then detected dialogs that did not complete the task, using N-gram probability models or a Support Vector Machine with N-gram feature vectors trained using manually classified dialogs. Offline and on-line detection experiments were conducted on a large amount of real data, and the results show that our proposed method achieved good classification performance.

KW - Breakdowns in dialog

KW - N-gram

KW - Spoken dialog system

KW - Task incomplete dialog detection

UR - http://www.scopus.com/inward/record.url?scp=84865793013&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865793013&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84865793013

SP - 1305

EP - 1308

BT - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

ER -