@inproceedings{zhao-kawahara-2018-unified,
title = "A Unified Neural Architecture for Joint Dialog Act Segmentation and Recognition in Spoken Dialog System",
author = "Zhao, Tianyu and
Kawahara, Tatsuya",
editor = "Komatani, Kazunori and
Litman, Diane and
Yu, Kai and
Papangelis, Alex and
Cavedon, Lawrence and
Nakano, Mikio",
booktitle = "Proceedings of the 19th Annual {SIG}dial Meeting on Discourse and Dialogue",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-5021",
doi = "10.18653/v1/W18-5021",
pages = "201--208",
abstract = "In spoken dialog systems (SDSs), dialog act (DA) segmentation and recognition provide essential information for response generation. A majority of previous works assumed ground-truth segmentation of DA units, which is not available from automatic speech recognition (ASR) in SDS. We propose a unified architecture based on neural networks, which consists of a sequence tagger for segmentation and a classifier for recognition. The DA recognition model is based on hierarchical neural networks to incorporate the context of preceding sentences. We investigate sharing some layers of the two components so that they can be trained jointly and learn generalized features from both tasks. An evaluation on the Switchboard Dialog Act (SwDA) corpus shows that the jointly-trained models outperform independently-trained models, single-step models, and other reported results in DA segmentation, recognition, and joint tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-kawahara-2018-unified">
<titleInfo>
<title>A Unified Neural Architecture for Joint Dialog Act Segmentation and Recognition in Spoken Dialog System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazunori</namePart>
<namePart type="family">Komatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diane</namePart>
<namePart type="family">Litman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lawrence</namePart>
<namePart type="family">Cavedon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikio</namePart>
<namePart type="family">Nakano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In spoken dialog systems (SDSs), dialog act (DA) segmentation and recognition provide essential information for response generation. A majority of previous works assumed ground-truth segmentation of DA units, which is not available from automatic speech recognition (ASR) in SDS. We propose a unified architecture based on neural networks, which consists of a sequence tagger for segmentation and a classifier for recognition. The DA recognition model is based on hierarchical neural networks to incorporate the context of preceding sentences. We investigate sharing some layers of the two components so that they can be trained jointly and learn generalized features from both tasks. An evaluation on the Switchboard Dialog Act (SwDA) corpus shows that the jointly-trained models outperform independently-trained models, single-step models, and other reported results in DA segmentation, recognition, and joint tasks.</abstract>
<identifier type="citekey">zhao-kawahara-2018-unified</identifier>
<identifier type="doi">10.18653/v1/W18-5021</identifier>
<location>
<url>https://aclanthology.org/W18-5021</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>201</start>
<end>208</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Unified Neural Architecture for Joint Dialog Act Segmentation and Recognition in Spoken Dialog System
%A Zhao, Tianyu
%A Kawahara, Tatsuya
%Y Komatani, Kazunori
%Y Litman, Diane
%Y Yu, Kai
%Y Papangelis, Alex
%Y Cavedon, Lawrence
%Y Nakano, Mikio
%S Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F zhao-kawahara-2018-unified
%X In spoken dialog systems (SDSs), dialog act (DA) segmentation and recognition provide essential information for response generation. A majority of previous works assumed ground-truth segmentation of DA units, which is not available from automatic speech recognition (ASR) in SDS. We propose a unified architecture based on neural networks, which consists of a sequence tagger for segmentation and a classifier for recognition. The DA recognition model is based on hierarchical neural networks to incorporate the context of preceding sentences. We investigate sharing some layers of the two components so that they can be trained jointly and learn generalized features from both tasks. An evaluation on the Switchboard Dialog Act (SwDA) corpus shows that the jointly-trained models outperform independently-trained models, single-step models, and other reported results in DA segmentation, recognition, and joint tasks.
%R 10.18653/v1/W18-5021
%U https://aclanthology.org/W18-5021
%U https://doi.org/10.18653/v1/W18-5021
%P 201-208
Markdown (Informal)
[A Unified Neural Architecture for Joint Dialog Act Segmentation and Recognition in Spoken Dialog System](https://aclanthology.org/W18-5021) (Zhao & Kawahara, SIGDIAL 2018)
ACL