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 language | English |
|---|---|
| Title of host publication | Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH |
| Pages | 1305-1308 |
| Number of pages | 4 |
| Publication status | Published - 2011 |
| Externally published | Yes |
| Event | 12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011 - Florence, Italy Duration: Aug 27 2011 → Aug 31 2011 |
Other
| Other | 12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011 |
|---|---|
| Country | Italy |
| City | Florence |
| Period | 8/27/11 → 8/31/11 |
Fingerprint
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
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 proceeding › Conference contribution
}
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 -