<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aksu-etal-2022-n">
    <titleInfo>
        <title>N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Taha</namePart>
        <namePart type="family">Aksu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhengyuan</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Min-Yen</namePart>
        <namePart type="family">Kan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nancy</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Smaranda</namePart>
            <namePart type="family">Muresan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Preslav</namePart>
            <namePart type="family">Nakov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dublin, Ireland</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Augmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure. In this work, we introduce an augmentation framework that utilizes belief state annotations to match turns from various dialogues and form new synthetic dialogues in a bottom-up manner. Unlike other augmentation strategies, it operates with as few as five examples. Our augmentation strategy yields significant improvements when both adapting a DST model to a new domain, and when adapting a language model to the DST task, on evaluations with TRADE and TOD-BERT models. Further analysis shows that our model performs better on seen values during training, and it is also more robust to unseen values. We conclude that exploiting belief state annotations enhances dialogue augmentation and results in improved models in n-shot training scenarios.</abstract>
    <identifier type="citekey">aksu-etal-2022-n</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-acl.131</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-acl.131</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>1659</start>
            <end>1671</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking
%A Aksu, Taha
%A Liu, Zhengyuan
%A Kan, Min-Yen
%A Chen, Nancy
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F aksu-etal-2022-n
%X Augmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure. In this work, we introduce an augmentation framework that utilizes belief state annotations to match turns from various dialogues and form new synthetic dialogues in a bottom-up manner. Unlike other augmentation strategies, it operates with as few as five examples. Our augmentation strategy yields significant improvements when both adapting a DST model to a new domain, and when adapting a language model to the DST task, on evaluations with TRADE and TOD-BERT models. Further analysis shows that our model performs better on seen values during training, and it is also more robust to unseen values. We conclude that exploiting belief state annotations enhances dialogue augmentation and results in improved models in n-shot training scenarios.
%R 10.18653/v1/2022.findings-acl.131
%U https://aclanthology.org/2022.findings-acl.131
%U https://doi.org/10.18653/v1/2022.findings-acl.131
%P 1659-1671

Markdown (Informal)

[N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking](https://aclanthology.org/2022.findings-acl.131) (Aksu et al., Findings 2022)

• N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking (Aksu et al., Findings 2022)

ACL

• Taha Aksu, Zhengyuan Liu, Min-Yen Kan, and Nancy Chen. 2022. N-Shot Learning for Augmenting Task-Oriented Dialogue State Tracking. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1659–1671, Dublin, Ireland. Association for Computational Linguistics.