<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="king-flanigan-2023-diverse">
    <titleInfo>
        <title>Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Brendan</namePart>
        <namePart type="family">King</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jeffrey</namePart>
        <namePart type="family">Flanigan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jordan</namePart>
            <namePart type="family">Boyd-Graber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Naoaki</namePart>
            <namePart type="family">Okazaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Toronto, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>There has been significant interest in zero and few-shot learning for dialogue state tracking (DST) due to the high cost of collecting and annotating task-oriented dialogues. Recent work has demonstrated that in-context learning requires very little data and zero parameter updates, and even outperforms trained methods in the few-shot setting. We propose RefPyDST, which advances the state of the art with three advancements to in-context learning for DST.First, we formulate DST as a Python programming task, explicitly modeling language coreference as variable reference in Python. Second, since in-context learning depends highly on the context examples, we propose a method to retrieve a diverse set of relevant examples to improve performance. Finally, we introduce a novel re-weighting method during decoding that takes into account probabilities of competing surface forms, and produces a more accurate dialogue state prediction. We evaluate our approach using MultiWOZ and achieve state-of-the-art multi-domain joint-goal accuracy in zero and few-shot settings.</abstract>
    <identifier type="citekey">king-flanigan-2023-diverse</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.344</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.344</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>5570</start>
            <end>5585</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking
%A King, Brendan
%A Flanigan, Jeffrey
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F king-flanigan-2023-diverse
%X There has been significant interest in zero and few-shot learning for dialogue state tracking (DST) due to the high cost of collecting and annotating task-oriented dialogues. Recent work has demonstrated that in-context learning requires very little data and zero parameter updates, and even outperforms trained methods in the few-shot setting. We propose RefPyDST, which advances the state of the art with three advancements to in-context learning for DST.First, we formulate DST as a Python programming task, explicitly modeling language coreference as variable reference in Python. Second, since in-context learning depends highly on the context examples, we propose a method to retrieve a diverse set of relevant examples to improve performance. Finally, we introduce a novel re-weighting method during decoding that takes into account probabilities of competing surface forms, and produces a more accurate dialogue state prediction. We evaluate our approach using MultiWOZ and achieve state-of-the-art multi-domain joint-goal accuracy in zero and few-shot settings.
%R 10.18653/v1/2023.findings-acl.344
%U https://aclanthology.org/2023.findings-acl.344
%U https://doi.org/10.18653/v1/2023.findings-acl.344
%P 5570-5585

Markdown (Informal)

[Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking](https://aclanthology.org/2023.findings-acl.344) (King & Flanigan, Findings 2023)

• Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking (King & Flanigan, Findings 2023)

ACL

• Brendan King and Jeffrey Flanigan. 2023. Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking. In Findings of the Association for Computational Linguistics: ACL 2023, pages 5570–5585, Toronto, Canada. Association for Computational Linguistics.