An Utterance Prediction Method Based on the Topic Transition Model

Yoichi YAMASHITA; Takashi HIRAMATSU; Osamu KAKUSHO; Riichiro MIZOGUCHI

An Utterance Prediction Method Based on the Topic Transition Model

Yoichi YAMASHITA, Takashi HIRAMATSU, Osamu KAKUSHO, Riichiro MIZOGUCHI

Full Text Views

0

Share
Cite this

Summary :

This paper describes a method for predicting the user's next utterances in spoken dialog based on the topic transition model, named TPN. Some templates are prepared for each utterance pair pattern modeled by SR-plan. They are represented in terms of five kinds of topic-independent constituents in sentences. The topic of an utterance is predicted based on the TPN model and it instantiates the templates. The language processing unit analyzes the speech recognition result using the templates. An experiment shows that the introduction of the TPN model improves the performance of utterance recognition and it drastically reduces the search space of candidates in the input bunsetsu lattice.

Publication: IEICE TRANSACTIONS on Information Vol.E78-D No.6 pp.622-628

Publication Date: 1995/06/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Issue on Spoken Language Processing)

Category

Cite this

Copy

Yoichi YAMASHITA, Takashi HIRAMATSU, Osamu KAKUSHO, Riichiro MIZOGUCHI, "An Utterance Prediction Method Based on the Topic Transition Model" in IEICE TRANSACTIONS on Information, vol. E78-D, no. 6, pp. 622-628, June 1995, doi: .
Abstract: This paper describes a method for predicting the user's next utterances in spoken dialog based on the topic transition model, named TPN. Some templates are prepared for each utterance pair pattern modeled by SR-plan. They are represented in terms of five kinds of topic-independent constituents in sentences. The topic of an utterance is predicted based on the TPN model and it instantiates the templates. The language processing unit analyzes the speech recognition result using the templates. An experiment shows that the introduction of the TPN model improves the performance of utterance recognition and it drastically reduces the search space of candidates in the input bunsetsu lattice.
URL: https://globals.ieice.org/en_transactions/information/10.1587/e78-d_6_622/_p

Copy

@ARTICLE{e78-d_6_622,
author={Yoichi YAMASHITA, Takashi HIRAMATSU, Osamu KAKUSHO, Riichiro MIZOGUCHI, },
journal={IEICE TRANSACTIONS on Information},
title={An Utterance Prediction Method Based on the Topic Transition Model},
year={1995},
volume={E78-D},
number={6},
pages={622-628},
abstract={This paper describes a method for predicting the user's next utterances in spoken dialog based on the topic transition model, named TPN. Some templates are prepared for each utterance pair pattern modeled by SR-plan. They are represented in terms of five kinds of topic-independent constituents in sentences. The topic of an utterance is predicted based on the TPN model and it instantiates the templates. The language processing unit analyzes the speech recognition result using the templates. An experiment shows that the introduction of the TPN model improves the performance of utterance recognition and it drastically reduces the search space of candidates in the input bunsetsu lattice.},
keywords={},
doi={},
ISSN={},
month={June},}

Copy

TY - JOUR
TI - An Utterance Prediction Method Based on the Topic Transition Model
T2 - IEICE TRANSACTIONS on Information
SP - 622
EP - 628
AU - Yoichi YAMASHITA
AU - Takashi HIRAMATSU
AU - Osamu KAKUSHO
AU - Riichiro MIZOGUCHI
PY - 1995
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E78-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 1995
AB - This paper describes a method for predicting the user's next utterances in spoken dialog based on the topic transition model, named TPN. Some templates are prepared for each utterance pair pattern modeled by SR-plan. They are represented in terms of five kinds of topic-independent constituents in sentences. The topic of an utterance is predicted based on the TPN model and it instantiates the templates. The language processing unit analyzes the speech recognition result using the templates. An experiment shows that the introduction of the TPN model improves the performance of utterance recognition and it drastically reduces the search space of candidates in the input bunsetsu lattice.
ER -