Topic estimation with domain extensibility for guiding user's out-of-grammar utterances in multi-domain spoken dialogue systems

Satoshi Ikeda, Kazunori Komatani, Tetsuya Ogata, Hiroshi G. Okuno

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

Abstract

In a multi-domain spoken dialogue system, a user's utterances are more prone to be out-of-grammar, because this kind of system deals with more tasks than a single-domain system. We defined a topic as a domain about which users want to find more information, and we developed a method of recovering out-of-grammar utterances based on topic estimation, i.e., by providing a help message in the estimated domain. Moreover, the domain extensibility, that is, to facilitate adding new domains, should be inherently retained in multi-domain systems. We therefore collected documents from the Web as training data for topic estimation. Because the data contained not a few noises, we used Latent Semantic Mapping (LSM), which enables robust topic estimation by removing the effect of noise from the data. The experimental results based on using 272 utterances collected with a Woz-like method showed that our method increased the topic estimation accuracy by 23.1 points from the baseline.

Original languageEnglish
Title of host publicationInternational Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007
Pages2057-2060
Number of pages4
Volume3
Publication statusPublished - 2007
Externally publishedYes
Event8th Annual Conference of the International Speech Communication Association, Interspeech 2007 - Antwerp
Duration: 2007 Aug 272007 Aug 31

Other

Other8th Annual Conference of the International Speech Communication Association, Interspeech 2007
CityAntwerp
Period07/8/2707/8/31

Fingerprint

Spoken Dialogue Systems
Grammar
grammar
communication technology
Semantics
semantics
Baseline
Experimental Results

Keywords

  • Multi-domain spoken dialogue system
  • Out-of-grammar utterance
  • Topic estimation

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Modelling and Simulation
  • Linguistics and Language
  • Communication

Cite this

Ikeda, S., Komatani, K., Ogata, T., & Okuno, H. G. (2007). Topic estimation with domain extensibility for guiding user's out-of-grammar utterances in multi-domain spoken dialogue systems. In International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007 (Vol. 3, pp. 2057-2060)

Topic estimation with domain extensibility for guiding user's out-of-grammar utterances in multi-domain spoken dialogue systems. / Ikeda, Satoshi; Komatani, Kazunori; Ogata, Tetsuya; Okuno, Hiroshi G.

International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007. Vol. 3 2007. p. 2057-2060.

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

Ikeda, S, Komatani, K, Ogata, T & Okuno, HG 2007, Topic estimation with domain extensibility for guiding user's out-of-grammar utterances in multi-domain spoken dialogue systems. in International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007. vol. 3, pp. 2057-2060, 8th Annual Conference of the International Speech Communication Association, Interspeech 2007, Antwerp, 07/8/27.
Ikeda S, Komatani K, Ogata T, Okuno HG. Topic estimation with domain extensibility for guiding user's out-of-grammar utterances in multi-domain spoken dialogue systems. In International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007. Vol. 3. 2007. p. 2057-2060
Ikeda, Satoshi ; Komatani, Kazunori ; Ogata, Tetsuya ; Okuno, Hiroshi G. / Topic estimation with domain extensibility for guiding user's out-of-grammar utterances in multi-domain spoken dialogue systems. International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007. Vol. 3 2007. pp. 2057-2060
@inproceedings{56cc94fa6b68444fae1ba99778202a20,
title = "Topic estimation with domain extensibility for guiding user's out-of-grammar utterances in multi-domain spoken dialogue systems",
abstract = "In a multi-domain spoken dialogue system, a user's utterances are more prone to be out-of-grammar, because this kind of system deals with more tasks than a single-domain system. We defined a topic as a domain about which users want to find more information, and we developed a method of recovering out-of-grammar utterances based on topic estimation, i.e., by providing a help message in the estimated domain. Moreover, the domain extensibility, that is, to facilitate adding new domains, should be inherently retained in multi-domain systems. We therefore collected documents from the Web as training data for topic estimation. Because the data contained not a few noises, we used Latent Semantic Mapping (LSM), which enables robust topic estimation by removing the effect of noise from the data. The experimental results based on using 272 utterances collected with a Woz-like method showed that our method increased the topic estimation accuracy by 23.1 points from the baseline.",
keywords = "Multi-domain spoken dialogue system, Out-of-grammar utterance, Topic estimation",
author = "Satoshi Ikeda and Kazunori Komatani and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2007",
language = "English",
isbn = "9781605603162",
volume = "3",
pages = "2057--2060",
booktitle = "International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007",

}

TY - GEN

T1 - Topic estimation with domain extensibility for guiding user's out-of-grammar utterances in multi-domain spoken dialogue systems

AU - Ikeda, Satoshi

AU - Komatani, Kazunori

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2007

Y1 - 2007

N2 - In a multi-domain spoken dialogue system, a user's utterances are more prone to be out-of-grammar, because this kind of system deals with more tasks than a single-domain system. We defined a topic as a domain about which users want to find more information, and we developed a method of recovering out-of-grammar utterances based on topic estimation, i.e., by providing a help message in the estimated domain. Moreover, the domain extensibility, that is, to facilitate adding new domains, should be inherently retained in multi-domain systems. We therefore collected documents from the Web as training data for topic estimation. Because the data contained not a few noises, we used Latent Semantic Mapping (LSM), which enables robust topic estimation by removing the effect of noise from the data. The experimental results based on using 272 utterances collected with a Woz-like method showed that our method increased the topic estimation accuracy by 23.1 points from the baseline.

AB - In a multi-domain spoken dialogue system, a user's utterances are more prone to be out-of-grammar, because this kind of system deals with more tasks than a single-domain system. We defined a topic as a domain about which users want to find more information, and we developed a method of recovering out-of-grammar utterances based on topic estimation, i.e., by providing a help message in the estimated domain. Moreover, the domain extensibility, that is, to facilitate adding new domains, should be inherently retained in multi-domain systems. We therefore collected documents from the Web as training data for topic estimation. Because the data contained not a few noises, we used Latent Semantic Mapping (LSM), which enables robust topic estimation by removing the effect of noise from the data. The experimental results based on using 272 utterances collected with a Woz-like method showed that our method increased the topic estimation accuracy by 23.1 points from the baseline.

KW - Multi-domain spoken dialogue system

KW - Out-of-grammar utterance

KW - Topic estimation

UR - http://www.scopus.com/inward/record.url?scp=56149089583&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56149089583&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:56149089583

SN - 9781605603162

VL - 3

SP - 2057

EP - 2060

BT - International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007

ER -