An Integrated Dialogue Analysis Model for Determining Speech Acts and Discourse Structures
Summary :
Analysis of speech acts and discourse structures is essential to a dialogue understanding system because speech acts and discourse structures are closely tied with the speaker's intention. However, it has been difficult to infer a speech act and a discourse structure from a surface utterance because they highly depend on the context of the utterance. We propose a statistical dialogue analysis model to determine discourse structures as well as speech acts using a maximum entropy model. The model can automatically acquire probabilistic discourse knowledge from an annotated dialogue corpus. Moreover, the model can analyze speech acts and discourse structures in one framework. In the experiment, the model showed better performance than other previous works.
- Publication
- IEICE TRANSACTIONS on Information Vol.E88-D No.1 pp.150-157
- Publication Date
- 2005/01/01
- Publicized
- Online ISSN
- DOI
- 10.1093/ietisy/e88-d.1.150
- Type of Manuscript
- PAPER
- Category
- Natural Language Processing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Won Seug CHOI, Harksoo KIM, Jungyun SEO, "An Integrated Dialogue Analysis Model for Determining Speech Acts and Discourse Structures" in IEICE TRANSACTIONS on Information,
vol. E88-D, no. 1, pp. 150-157, January 2005, doi: 10.1093/ietisy/e88-d.1.150.
Abstract: Analysis of speech acts and discourse structures is essential to a dialogue understanding system because speech acts and discourse structures are closely tied with the speaker's intention. However, it has been difficult to infer a speech act and a discourse structure from a surface utterance because they highly depend on the context of the utterance. We propose a statistical dialogue analysis model to determine discourse structures as well as speech acts using a maximum entropy model. The model can automatically acquire probabilistic discourse knowledge from an annotated dialogue corpus. Moreover, the model can analyze speech acts and discourse structures in one framework. In the experiment, the model showed better performance than other previous works.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e88-d.1.150/_p
Copy
@ARTICLE{e88-d_1_150,
author={Won Seug CHOI, Harksoo KIM, Jungyun SEO, },
journal={IEICE TRANSACTIONS on Information},
title={An Integrated Dialogue Analysis Model for Determining Speech Acts and Discourse Structures},
year={2005},
volume={E88-D},
number={1},
pages={150-157},
abstract={Analysis of speech acts and discourse structures is essential to a dialogue understanding system because speech acts and discourse structures are closely tied with the speaker's intention. However, it has been difficult to infer a speech act and a discourse structure from a surface utterance because they highly depend on the context of the utterance. We propose a statistical dialogue analysis model to determine discourse structures as well as speech acts using a maximum entropy model. The model can automatically acquire probabilistic discourse knowledge from an annotated dialogue corpus. Moreover, the model can analyze speech acts and discourse structures in one framework. In the experiment, the model showed better performance than other previous works.},
keywords={},
doi={10.1093/ietisy/e88-d.1.150},
ISSN={},
month={January},}
Copy
TY - JOUR
TI - An Integrated Dialogue Analysis Model for Determining Speech Acts and Discourse Structures
T2 - IEICE TRANSACTIONS on Information
SP - 150
EP - 157
AU - Won Seug CHOI
AU - Harksoo KIM
AU - Jungyun SEO
PY - 2005
DO - 10.1093/ietisy/e88-d.1.150
JO - IEICE TRANSACTIONS on Information
SN -
VL - E88-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2005
AB - Analysis of speech acts and discourse structures is essential to a dialogue understanding system because speech acts and discourse structures are closely tied with the speaker's intention. However, it has been difficult to infer a speech act and a discourse structure from a surface utterance because they highly depend on the context of the utterance. We propose a statistical dialogue analysis model to determine discourse structures as well as speech acts using a maximum entropy model. The model can automatically acquire probabilistic discourse knowledge from an annotated dialogue corpus. Moreover, the model can analyze speech acts and discourse structures in one framework. In the experiment, the model showed better performance than other previous works.
ER -
English
