<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="snell-etal-2022-context">
    <titleInfo>
        <title>Context-Aware Language Modeling for Goal-Oriented Dialogue Systems</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Charlie</namePart>
        <namePart type="family">Snell</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sherry</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Justin</namePart>
        <namePart type="family">Fu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yi</namePart>
        <namePart type="family">Su</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sergey</namePart>
        <namePart type="family">Levine</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marine</namePart>
            <namePart type="family">Carpuat</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marie-Catherine</namePart>
            <namePart type="family">de Marneffe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ivan</namePart>
            <namePart type="given">Vladimir</namePart>
            <namePart type="family">Meza Ruiz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Seattle, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards completing a specific task without sacrificing language quality remains an open question. In this work, we formulate goal-oriented dialogue as a partially observed Markov decision process, interpreting the language model as a representation of both the dynamics and the policy. This view allows us to extend techniques from learning-based control, such as task relabeling, to derive a simple and effective method to finetune language models in a goal-aware way, leading to significantly improved task performance. We additionally introduce a number of training strategies that serve to better focus the model on the task at hand. We evaluate our method, Context-Aware Language Models (CALM), on a practical flight-booking task using AirDialogue. Empirically, CALM outperforms the state-of-the-art method by 7% in terms of task success, matching human-level task performance.</abstract>
    <identifier type="citekey">snell-etal-2022-context</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-naacl.181</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-naacl.181</url>
    </location>
    <part>
        <date>2022-07</date>
        <extent unit="page">
            <start>2351</start>
            <end>2366</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Context-Aware Language Modeling for Goal-Oriented Dialogue Systems
%A Snell, Charlie
%A Yang, Sherry
%A Fu, Justin
%A Su, Yi
%A Levine, Sergey
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F snell-etal-2022-context
%X Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards completing a specific task without sacrificing language quality remains an open question. In this work, we formulate goal-oriented dialogue as a partially observed Markov decision process, interpreting the language model as a representation of both the dynamics and the policy. This view allows us to extend techniques from learning-based control, such as task relabeling, to derive a simple and effective method to finetune language models in a goal-aware way, leading to significantly improved task performance. We additionally introduce a number of training strategies that serve to better focus the model on the task at hand. We evaluate our method, Context-Aware Language Models (CALM), on a practical flight-booking task using AirDialogue. Empirically, CALM outperforms the state-of-the-art method by 7% in terms of task success, matching human-level task performance.
%R 10.18653/v1/2022.findings-naacl.181
%U https://aclanthology.org/2022.findings-naacl.181
%U https://doi.org/10.18653/v1/2022.findings-naacl.181
%P 2351-2366

Markdown (Informal)

[Context-Aware Language Modeling for Goal-Oriented Dialogue Systems](https://aclanthology.org/2022.findings-naacl.181) (Snell et al., Findings 2022)

• Context-Aware Language Modeling for Goal-Oriented Dialogue Systems (Snell et al., Findings 2022)

ACL

• Charlie Snell, Sherry Yang, Justin Fu, Yi Su, and Sergey Levine. 2022. Context-Aware Language Modeling for Goal-Oriented Dialogue Systems. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2351–2366, Seattle, United States. Association for Computational Linguistics.