@inproceedings{wu-etal-2020-improving-limited,
title = "Improving Limited Labeled Dialogue State Tracking with Self-Supervision",
author = "Wu, Chien-Sheng and
Hoi, Steven C.H. and
Xiong, Caiming",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.400",
doi = "10.18653/v1/2020.findings-emnlp.400",
pages = "4462--4472",
abstract = "Existing dialogue state tracking (DST) models require plenty of labeled data. However, collecting high-quality labels is costly, especially when the number of domains increases. In this paper, we address a practical DST problem that is rarely discussed, i.e., learning efficiently with limited labeled data. We present and investigate two self-supervised objectives: preserving latent consistency and modeling conversational behavior. We encourage a DST model to have consistent latent distributions given a perturbed input, making it more robust to an unseen scenario. We also add an auxiliary utterance generation task, modeling a potential correlation between conversational behavior and dialogue states. The experimental results show that our proposed self-supervised signals can improve joint goal accuracy by 8.95{\%} when only 1{\%} labeled data is used on the MultiWOZ dataset. We can achieve an additional 1.76{\%} improvement if some unlabeled data is jointly trained as semi-supervised learning. We analyze and visualize how our proposed self-supervised signals help the DST task and hope to stimulate future data-efficient DST research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2020-improving-limited">
<titleInfo>
<title>Improving Limited Labeled Dialogue State Tracking with Self-Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chien-Sheng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="given">C.H.</namePart>
<namePart type="family">Hoi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caiming</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing dialogue state tracking (DST) models require plenty of labeled data. However, collecting high-quality labels is costly, especially when the number of domains increases. In this paper, we address a practical DST problem that is rarely discussed, i.e., learning efficiently with limited labeled data. We present and investigate two self-supervised objectives: preserving latent consistency and modeling conversational behavior. We encourage a DST model to have consistent latent distributions given a perturbed input, making it more robust to an unseen scenario. We also add an auxiliary utterance generation task, modeling a potential correlation between conversational behavior and dialogue states. The experimental results show that our proposed self-supervised signals can improve joint goal accuracy by 8.95% when only 1% labeled data is used on the MultiWOZ dataset. We can achieve an additional 1.76% improvement if some unlabeled data is jointly trained as semi-supervised learning. We analyze and visualize how our proposed self-supervised signals help the DST task and hope to stimulate future data-efficient DST research.</abstract>
<identifier type="citekey">wu-etal-2020-improving-limited</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.400</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.400</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>4462</start>
<end>4472</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Limited Labeled Dialogue State Tracking with Self-Supervision
%A Wu, Chien-Sheng
%A Hoi, Steven C.H.
%A Xiong, Caiming
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F wu-etal-2020-improving-limited
%X Existing dialogue state tracking (DST) models require plenty of labeled data. However, collecting high-quality labels is costly, especially when the number of domains increases. In this paper, we address a practical DST problem that is rarely discussed, i.e., learning efficiently with limited labeled data. We present and investigate two self-supervised objectives: preserving latent consistency and modeling conversational behavior. We encourage a DST model to have consistent latent distributions given a perturbed input, making it more robust to an unseen scenario. We also add an auxiliary utterance generation task, modeling a potential correlation between conversational behavior and dialogue states. The experimental results show that our proposed self-supervised signals can improve joint goal accuracy by 8.95% when only 1% labeled data is used on the MultiWOZ dataset. We can achieve an additional 1.76% improvement if some unlabeled data is jointly trained as semi-supervised learning. We analyze and visualize how our proposed self-supervised signals help the DST task and hope to stimulate future data-efficient DST research.
%R 10.18653/v1/2020.findings-emnlp.400
%U https://aclanthology.org/2020.findings-emnlp.400
%U https://doi.org/10.18653/v1/2020.findings-emnlp.400
%P 4462-4472
Markdown (Informal)
[Improving Limited Labeled Dialogue State Tracking with Self-Supervision](https://aclanthology.org/2020.findings-emnlp.400) (Wu et al., Findings 2020)
ACL