Relating the semantics of dialogue acts to linguistic roperties: A machine learning perspective through lexical cues

Alex C. Fang; Harry Bunt; Jing Cao; Xiaoyue Liu

doi:10.1109/ICSC.2011.32

Relating the semantics of dialogue acts to linguistic roperties: A machine learning perspective through lexical cues

Alex C. Fang, Harry Bunt, Jing Cao, Xiaoyue Liu

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

7 Citations (Scopus)

Abstract

This paper describes a corpus-based investigation of dialogue acts. In particular, it attempts to answer questions about the empirical distribution of dialogue acts and to what extent dialogue acts can be automatically predicted from their lexical features. The Switchboard Dialogue Act Corpus is adopted and the SWBD-DAMSL tags used for automatic prediction. We show that 60-70% of the dialogue acts can be predicted from lexical features alone depending on different levels of granularity. We also present a mapping from SWBDDAMSL tags to the tags of the new ISO standard for dialogue act annotation, as part of an ongoing investigation into the relationship between the structure and granularity of the tag set and classification accuracy. The paper concludes with discussions and suggestions for future work. © 2011 IEEE.

Original language	English
Title of host publication	Proceedings - 5th IEEE International Conference on Semantic Computing, ICSC 2011
Pages	490-497
DOIs	https://doi.org/10.1109/ICSC.2011.32
Publication status	Published - 2011
Event	5th Annual IEEE International Conference on Semantic Computing, ICSC 2011 - Palo Alto, CA, United States Duration: 18 Sept 2011 → 21 Sept 2011

Conference

Conference	5th Annual IEEE International Conference on Semantic Computing, ICSC 2011
Place	United States
City	Palo Alto, CA
Period	18/09/11 → 21/09/11

Research Keywords

Automatic classification
Dialogue act
ISO dialogue annotation standard
SWBDDAMSL
Switchboard corpus

Access Output

10.1109/ICSC.2011.32

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{6ac18b6c200943b3b4f2913d1c9d9025,

title = "Relating the semantics of dialogue acts to linguistic roperties: A machine learning perspective through lexical cues",

abstract = "This paper describes a corpus-based investigation of dialogue acts. In particular, it attempts to answer questions about the empirical distribution of dialogue acts and to what extent dialogue acts can be automatically predicted from their lexical features. The Switchboard Dialogue Act Corpus is adopted and the SWBD-DAMSL tags used for automatic prediction. We show that 60-70% of the dialogue acts can be predicted from lexical features alone depending on different levels of granularity. We also present a mapping from SWBDDAMSL tags to the tags of the new ISO standard for dialogue act annotation, as part of an ongoing investigation into the relationship between the structure and granularity of the tag set and classification accuracy. The paper concludes with discussions and suggestions for future work. {\textcopyright} 2011 IEEE.",

keywords = "Automatic classification, Dialogue act, ISO dialogue annotation standard, SWBDDAMSL, Switchboard corpus",

author = "Fang, {Alex C.} and Harry Bunt and Jing Cao and Xiaoyue Liu",

year = "2011",

doi = "10.1109/ICSC.2011.32",

language = "English",

isbn = "9780769544922",

pages = "490--497",

booktitle = "Proceedings - 5th IEEE International Conference on Semantic Computing, ICSC 2011",

note = "5th Annual IEEE International Conference on Semantic Computing, ICSC 2011 ; Conference date: 18-09-2011 Through 21-09-2011",

}

Fang, AC, Bunt, H, Cao, J & Liu, X 2011, Relating the semantics of dialogue acts to linguistic roperties: A machine learning perspective through lexical cues. in Proceedings - 5th IEEE International Conference on Semantic Computing, ICSC 2011., 6061505, pp. 490-497, 5th Annual IEEE International Conference on Semantic Computing, ICSC 2011, Palo Alto, CA, United States, 18/09/11. https://doi.org/10.1109/ICSC.2011.32

Relating the semantics of dialogue acts to linguistic roperties: A machine learning perspective through lexical cues. / Fang, Alex C.; Bunt, Harry; Cao, Jing et al.
Proceedings - 5th IEEE International Conference on Semantic Computing, ICSC 2011. 2011. p. 490-497 6061505.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Relating the semantics of dialogue acts to linguistic roperties

T2 - 5th Annual IEEE International Conference on Semantic Computing, ICSC 2011

AU - Fang, Alex C.

AU - Bunt, Harry

AU - Cao, Jing

AU - Liu, Xiaoyue

PY - 2011

Y1 - 2011

N2 - This paper describes a corpus-based investigation of dialogue acts. In particular, it attempts to answer questions about the empirical distribution of dialogue acts and to what extent dialogue acts can be automatically predicted from their lexical features. The Switchboard Dialogue Act Corpus is adopted and the SWBD-DAMSL tags used for automatic prediction. We show that 60-70% of the dialogue acts can be predicted from lexical features alone depending on different levels of granularity. We also present a mapping from SWBDDAMSL tags to the tags of the new ISO standard for dialogue act annotation, as part of an ongoing investigation into the relationship between the structure and granularity of the tag set and classification accuracy. The paper concludes with discussions and suggestions for future work. © 2011 IEEE.

AB - This paper describes a corpus-based investigation of dialogue acts. In particular, it attempts to answer questions about the empirical distribution of dialogue acts and to what extent dialogue acts can be automatically predicted from their lexical features. The Switchboard Dialogue Act Corpus is adopted and the SWBD-DAMSL tags used for automatic prediction. We show that 60-70% of the dialogue acts can be predicted from lexical features alone depending on different levels of granularity. We also present a mapping from SWBDDAMSL tags to the tags of the new ISO standard for dialogue act annotation, as part of an ongoing investigation into the relationship between the structure and granularity of the tag set and classification accuracy. The paper concludes with discussions and suggestions for future work. © 2011 IEEE.

KW - Automatic classification

KW - Dialogue act

KW - ISO dialogue annotation standard

KW - SWBDDAMSL

KW - Switchboard corpus

UR - http://www.scopus.com/inward/record.url?scp=81255205450&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-81255205450&origin=recordpage

U2 - 10.1109/ICSC.2011.32

DO - 10.1109/ICSC.2011.32

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9780769544922

SP - 490

EP - 497

BT - Proceedings - 5th IEEE International Conference on Semantic Computing, ICSC 2011

Y2 - 18 September 2011 through 21 September 2011

ER -

Relating the semantics of dialogue acts to linguistic roperties: A machine learning perspective through lexical cues

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this