@inproceedings{sharma-etal-2019-improving,
title = "Improving Dialogue State Tracking by Discerning the Relevant Context",
author = "Sharma, Sanuj and
Choubey, Prafulla Kumar and
Huang, Ruihong",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1057",
doi = "10.18653/v1/N19-1057",
pages = "576--581",
abstract = "A typical conversation comprises of multiple turns between participants where they go back and forth between different topics. At each user turn, dialogue state tracking (DST) aims to estimate user{'}s goal by processing the current utterance. However, in many turns, users implicitly refer to the previous goal, necessitating the use of relevant dialogue history. Nonetheless, distinguishing relevant history is challenging and a popular method of using dialogue recency for that is inefficient. We, therefore, propose a novel framework for DST that identifies relevant historical context by referring to the past utterances where a particular slot-value changes and uses that together with weighted system utterance to identify the relevant context. Specifically, we use the current user utterance and the most recent system utterance to determine the relevance of a system utterance. Empirical analyses show that our method improves joint goal accuracy by 2.75{\%} and 2.36{\%} on WoZ 2.0 and Multi-WoZ restaurant domain datasets respectively over the previous state-of-the-art GLAD model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharma-etal-2019-improving">
<titleInfo>
<title>Improving Dialogue State Tracking by Discerning the Relevant Context</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanuj</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prafulla</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Choubey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruihong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A typical conversation comprises of multiple turns between participants where they go back and forth between different topics. At each user turn, dialogue state tracking (DST) aims to estimate user’s goal by processing the current utterance. However, in many turns, users implicitly refer to the previous goal, necessitating the use of relevant dialogue history. Nonetheless, distinguishing relevant history is challenging and a popular method of using dialogue recency for that is inefficient. We, therefore, propose a novel framework for DST that identifies relevant historical context by referring to the past utterances where a particular slot-value changes and uses that together with weighted system utterance to identify the relevant context. Specifically, we use the current user utterance and the most recent system utterance to determine the relevance of a system utterance. Empirical analyses show that our method improves joint goal accuracy by 2.75% and 2.36% on WoZ 2.0 and Multi-WoZ restaurant domain datasets respectively over the previous state-of-the-art GLAD model.</abstract>
<identifier type="citekey">sharma-etal-2019-improving</identifier>
<identifier type="doi">10.18653/v1/N19-1057</identifier>
<location>
<url>https://aclanthology.org/N19-1057</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>576</start>
<end>581</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Dialogue State Tracking by Discerning the Relevant Context
%A Sharma, Sanuj
%A Choubey, Prafulla Kumar
%A Huang, Ruihong
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F sharma-etal-2019-improving
%X A typical conversation comprises of multiple turns between participants where they go back and forth between different topics. At each user turn, dialogue state tracking (DST) aims to estimate user’s goal by processing the current utterance. However, in many turns, users implicitly refer to the previous goal, necessitating the use of relevant dialogue history. Nonetheless, distinguishing relevant history is challenging and a popular method of using dialogue recency for that is inefficient. We, therefore, propose a novel framework for DST that identifies relevant historical context by referring to the past utterances where a particular slot-value changes and uses that together with weighted system utterance to identify the relevant context. Specifically, we use the current user utterance and the most recent system utterance to determine the relevance of a system utterance. Empirical analyses show that our method improves joint goal accuracy by 2.75% and 2.36% on WoZ 2.0 and Multi-WoZ restaurant domain datasets respectively over the previous state-of-the-art GLAD model.
%R 10.18653/v1/N19-1057
%U https://aclanthology.org/N19-1057
%U https://doi.org/10.18653/v1/N19-1057
%P 576-581
Markdown (Informal)
[Improving Dialogue State Tracking by Discerning the Relevant Context](https://aclanthology.org/N19-1057) (Sharma et al., NAACL 2019)
ACL
- Sanuj Sharma, Prafulla Kumar Choubey, and Ruihong Huang. 2019. Improving Dialogue State Tracking by Discerning the Relevant Context. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 576–581, Minneapolis, Minnesota. Association for Computational Linguistics.