<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-stabilized">
    <titleInfo>
        <title>Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Derek</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kun</namePart>
        <namePart type="family">Qian</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhou</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EACL 2023</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabelle</namePart>
            <namePart type="family">Augenstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dubrovnik, Croatia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Prompt-based methods with large pre-trained language models (PLMs) have shown impressive unaided performance across many NLP tasks. These models improve even further with the addition of a few labeled in-context exemplars to guide output generation. However, for more complex tasks such as dialogue state tracking (DST), designing prompts that reliably convey the desired intent is nontrivial, leading to unstable results. Furthermore, building in-context exemplars for dialogue tasks is difficult because conversational contexts are long while model input lengths are relatively short. To overcome these issues we first adapt a meta-learning scheme to the dialogue domain which stabilizes the ability of the model to perform well under various prompts. We additionally design a novel training method to improve upon vanilla retrieval mechanisms to find ideal in-context examples. Finally, we introduce a saliency model to limit dialogue text length, allowing us to include more exemplars per query. In effect, we are able to achieve highly competitive results for few-shot DST on MultiWOZ.</abstract>
    <identifier type="citekey">chen-etal-2023-stabilized</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-eacl.115</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-eacl.115</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>1551</start>
            <end>1564</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking
%A Chen, Derek
%A Qian, Kun
%A Yu, Zhou
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F chen-etal-2023-stabilized
%X Prompt-based methods with large pre-trained language models (PLMs) have shown impressive unaided performance across many NLP tasks. These models improve even further with the addition of a few labeled in-context exemplars to guide output generation. However, for more complex tasks such as dialogue state tracking (DST), designing prompts that reliably convey the desired intent is nontrivial, leading to unstable results. Furthermore, building in-context exemplars for dialogue tasks is difficult because conversational contexts are long while model input lengths are relatively short. To overcome these issues we first adapt a meta-learning scheme to the dialogue domain which stabilizes the ability of the model to perform well under various prompts. We additionally design a novel training method to improve upon vanilla retrieval mechanisms to find ideal in-context examples. Finally, we introduce a saliency model to limit dialogue text length, allowing us to include more exemplars per query. In effect, we are able to achieve highly competitive results for few-shot DST on MultiWOZ.
%R 10.18653/v1/2023.findings-eacl.115
%U https://aclanthology.org/2023.findings-eacl.115
%U https://doi.org/10.18653/v1/2023.findings-eacl.115
%P 1551-1564

Markdown (Informal)

[Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking](https://aclanthology.org/2023.findings-eacl.115) (Chen et al., Findings 2023)

• Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking (Chen et al., Findings 2023)

ACL

• Derek Chen, Kun Qian, and Zhou Yu. 2023. Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1551–1564, Dubrovnik, Croatia. Association for Computational Linguistics.