@inproceedings{mrksic-etal-2017-neural,
title = "Neural Belief Tracker: Data-Driven Dialogue State Tracking",
author = "Mrk\v si\'c, Nikola and
\'O S\'eaghdha, Diarmuid and
Wen, Tsung-Hsien and
Thomson, Blaise and
Young, Steve",
editor = "Barzilay, Regina and
Kan, Min-Yen",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-1163/",
doi = "10.18653/v1/P17-1163",
pages = "1777--1788",
abstract = "One of the core components of modern spoken dialogue systems is the belief tracker, which estimates the user's goal at every step of the dialogue. However, most current approaches have difficulty scaling to larger, more complex dialogue domains. This is due to their dependency on either: a) Spoken Language Understanding models that require large amounts of annotated training data; or b) hand-crafted lexicons for capturing some of the linguistic variation in users' language. We propose a novel Neural Belief Tracking (NBT) framework which overcomes these problems by building on recent advances in representation learning. NBT models reason over pre-trained word vectors, learning to compose them into distributed representations of user utterances and dialogue context. Our evaluation on two datasets shows that this approach surpasses past limitations, matching the performance of state-of-the-art models which rely on hand-crafted semantic lexicons and outperforming them when such lexicons are not provided."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mrksic-etal-2017-neural">
<titleInfo>
<title>Neural Belief Tracker: Data-Driven Dialogue State Tracking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Mrkšić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diarmuid</namePart>
<namePart type="family">Ó Séaghdha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsung-Hsien</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Blaise</namePart>
<namePart type="family">Thomson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steve</namePart>
<namePart type="family">Young</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Barzilay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One of the core components of modern spoken dialogue systems is the belief tracker, which estimates the user’s goal at every step of the dialogue. However, most current approaches have difficulty scaling to larger, more complex dialogue domains. This is due to their dependency on either: a) Spoken Language Understanding models that require large amounts of annotated training data; or b) hand-crafted lexicons for capturing some of the linguistic variation in users’ language. We propose a novel Neural Belief Tracking (NBT) framework which overcomes these problems by building on recent advances in representation learning. NBT models reason over pre-trained word vectors, learning to compose them into distributed representations of user utterances and dialogue context. Our evaluation on two datasets shows that this approach surpasses past limitations, matching the performance of state-of-the-art models which rely on hand-crafted semantic lexicons and outperforming them when such lexicons are not provided.</abstract>
<identifier type="citekey">mrksic-etal-2017-neural</identifier>
<identifier type="doi">10.18653/v1/P17-1163</identifier>
<location>
<url>https://aclanthology.org/P17-1163/</url>
</location>
<part>
<date>2017-07</date>
<extent unit="page">
<start>1777</start>
<end>1788</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Belief Tracker: Data-Driven Dialogue State Tracking
%A Mrkšić, Nikola
%A Ó Séaghdha, Diarmuid
%A Wen, Tsung-Hsien
%A Thomson, Blaise
%A Young, Steve
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F mrksic-etal-2017-neural
%X One of the core components of modern spoken dialogue systems is the belief tracker, which estimates the user’s goal at every step of the dialogue. However, most current approaches have difficulty scaling to larger, more complex dialogue domains. This is due to their dependency on either: a) Spoken Language Understanding models that require large amounts of annotated training data; or b) hand-crafted lexicons for capturing some of the linguistic variation in users’ language. We propose a novel Neural Belief Tracking (NBT) framework which overcomes these problems by building on recent advances in representation learning. NBT models reason over pre-trained word vectors, learning to compose them into distributed representations of user utterances and dialogue context. Our evaluation on two datasets shows that this approach surpasses past limitations, matching the performance of state-of-the-art models which rely on hand-crafted semantic lexicons and outperforming them when such lexicons are not provided.
%R 10.18653/v1/P17-1163
%U https://aclanthology.org/P17-1163/
%U https://doi.org/10.18653/v1/P17-1163
%P 1777-1788
Markdown (Informal)
[Neural Belief Tracker: Data-Driven Dialogue State Tracking](https://aclanthology.org/P17-1163/) (Mrkšić et al., ACL 2017)
ACL
- Nikola Mrkšić, Diarmuid Ó Séaghdha, Tsung-Hsien Wen, Blaise Thomson, and Steve Young. 2017. Neural Belief Tracker: Data-Driven Dialogue State Tracking. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1777–1788, Vancouver, Canada. Association for Computational Linguistics.