Ranking help message candidates based on robust grammar verification results and utterance history in spoken dialogue systems

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

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

1 Citation (Scopus)

Abstract

We address an issue of out-of-grammar (OOG) utterances in spoken dialogue systems by generating help messages for novice users. Help generation for OOG utterances is a challenging problem because language understanding (LU) results based on automatic speech recognition (ASR) results for such utterances are always erroneous as important words are often misrecognized or missed from such utterances. We first develop grammar verification for OOG utterances on the basis of a Weighted Finite-State Transducer (WFST). It robustly identifies a grammar rule that a user intends to utter, even when some important words are missed from the ASR result. We then adopt a ranking algorithm, RankBoost, whose features include the grammar verification results and the utterance history representing the user's experience.

Original languageEnglish
Title of host publicationProceedings of the SIGDIAL 2009 Conference: 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Pages314-321
Number of pages8
Publication statusPublished - 2009
Externally publishedYes
Event10th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2009 - London
Duration: 2009 Sep 112009 Sep 12

Other

Other10th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2009
CityLondon
Period09/9/1109/9/12

Fingerprint

Spoken Dialogue Systems
Speech recognition
Grammar
Ranking
Transducers
Automatic Speech Recognition
User Experience
Transducer
History

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Modelling and Simulation

Cite this

Komatani, K., Ikeda, S., Fukubayashi, Y., Ogata, T., & Okuno, H. G. (2009). Ranking help message candidates based on robust grammar verification results and utterance history in spoken dialogue systems. In Proceedings of the SIGDIAL 2009 Conference: 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue (pp. 314-321)

Ranking help message candidates based on robust grammar verification results and utterance history in spoken dialogue systems. / Komatani, Kazunori; Ikeda, Satoshi; Fukubayashi, Yuichiro; Ogata, Tetsuya; Okuno, Hiroshi G.

Proceedings of the SIGDIAL 2009 Conference: 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2009. p. 314-321.

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

Komatani, K, Ikeda, S, Fukubayashi, Y, Ogata, T & Okuno, HG 2009, Ranking help message candidates based on robust grammar verification results and utterance history in spoken dialogue systems. in Proceedings of the SIGDIAL 2009 Conference: 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue. pp. 314-321, 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue, SIGDIAL 2009, London, 09/9/11.
Komatani K, Ikeda S, Fukubayashi Y, Ogata T, Okuno HG. Ranking help message candidates based on robust grammar verification results and utterance history in spoken dialogue systems. In Proceedings of the SIGDIAL 2009 Conference: 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2009. p. 314-321
Komatani, Kazunori ; Ikeda, Satoshi ; Fukubayashi, Yuichiro ; Ogata, Tetsuya ; Okuno, Hiroshi G. / Ranking help message candidates based on robust grammar verification results and utterance history in spoken dialogue systems. Proceedings of the SIGDIAL 2009 Conference: 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 2009. pp. 314-321
@inproceedings{93145bb79bcc4a1aa6b2fc3d5457a707,
title = "Ranking help message candidates based on robust grammar verification results and utterance history in spoken dialogue systems",
abstract = "We address an issue of out-of-grammar (OOG) utterances in spoken dialogue systems by generating help messages for novice users. Help generation for OOG utterances is a challenging problem because language understanding (LU) results based on automatic speech recognition (ASR) results for such utterances are always erroneous as important words are often misrecognized or missed from such utterances. We first develop grammar verification for OOG utterances on the basis of a Weighted Finite-State Transducer (WFST). It robustly identifies a grammar rule that a user intends to utter, even when some important words are missed from the ASR result. We then adopt a ranking algorithm, RankBoost, whose features include the grammar verification results and the utterance history representing the user's experience.",
author = "Kazunori Komatani and Satoshi Ikeda and Yuichiro Fukubayashi and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2009",
language = "English",
isbn = "9781932432640",
pages = "314--321",
booktitle = "Proceedings of the SIGDIAL 2009 Conference: 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue",

}

TY - GEN

T1 - Ranking help message candidates based on robust grammar verification results and utterance history in spoken dialogue systems

AU - Komatani, Kazunori

AU - Ikeda, Satoshi

AU - Fukubayashi, Yuichiro

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2009

Y1 - 2009

N2 - We address an issue of out-of-grammar (OOG) utterances in spoken dialogue systems by generating help messages for novice users. Help generation for OOG utterances is a challenging problem because language understanding (LU) results based on automatic speech recognition (ASR) results for such utterances are always erroneous as important words are often misrecognized or missed from such utterances. We first develop grammar verification for OOG utterances on the basis of a Weighted Finite-State Transducer (WFST). It robustly identifies a grammar rule that a user intends to utter, even when some important words are missed from the ASR result. We then adopt a ranking algorithm, RankBoost, whose features include the grammar verification results and the utterance history representing the user's experience.

AB - We address an issue of out-of-grammar (OOG) utterances in spoken dialogue systems by generating help messages for novice users. Help generation for OOG utterances is a challenging problem because language understanding (LU) results based on automatic speech recognition (ASR) results for such utterances are always erroneous as important words are often misrecognized or missed from such utterances. We first develop grammar verification for OOG utterances on the basis of a Weighted Finite-State Transducer (WFST). It robustly identifies a grammar rule that a user intends to utter, even when some important words are missed from the ASR result. We then adopt a ranking algorithm, RankBoost, whose features include the grammar verification results and the utterance history representing the user's experience.

UR - http://www.scopus.com/inward/record.url?scp=78650023182&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650023182&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:78650023182

SN - 9781932432640

SP - 314

EP - 321

BT - Proceedings of the SIGDIAL 2009 Conference: 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue

ER -