Dialog-Act Recognition Using Discourse and Sentence Structure Information

Author

Zhou, Keyan ; Zong, Chengqing

Author_Institution

Inst. of Autom., Chinese Acad. of Sci., Beijing, China

fYear

2009

fDate

7-9 Dec. 2009

Firstpage

11

Lastpage

16

Abstract

Automatic recognition of Dialog-act (DA) is one of the most important processes in understanding spontaneous dialog. Most existing studies have been working on how to use various classifying methods in DA recognition; meanwhile, less attention has been paid to feature selection specifically. This paper introduces several textual features for DA recognizing, and proposes a novel usage for sentence structure features. Especially, this paper investigates the effect of discourse structure features in DA recognition, which are little studied before. The experimental results on both Chinese corpus and English Corpus show the selected features and feature combination rules significantly improve the overall performance. The accuracy of DA recognition rises from 77.05% to 88.21% on Chinese corpus, and from 59.08% to 64.92% as well on English corpus.

Keywords

feature extraction; interactive systems; linguistics; speech; dialog-act recognition; discourse structure features; feature selection; sentence structure information; Automation; Classification tree analysis; Decision trees; Entropy; Machine learning; Natural languages; Speech; Support vector machine classification; Support vector machines; Telephony; dialog-act recognition; discourse structure features; feature combination; feature selection; sentence structure features;

fLanguage

English

Publisher

ieee

Conference_Titel

Asian Language Processing, 2009. IALP '09. International Conference on

Conference_Location

Singapore

Print_ISBN

978-0-7695-3904-1

Type

conf

DOI

10.1109/IALP.2009.12

Filename

5380793