<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2024-continual">
    <titleInfo>
        <title>Continual Dialogue State Tracking via Reason-of-Select Distillation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yujie</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bo</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaoyu</namePart>
        <namePart type="family">Dong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zexin</namePart>
        <namePart type="family">Lu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Li-Ming</namePart>
        <namePart type="family">Zhan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiao-Ming</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Albert</namePart>
        <namePart type="family">Lam</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Lun-Wei</namePart>
            <namePart type="family">Ku</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andre</namePart>
            <namePart type="family">Martins</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Srikumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>An ideal dialogue system requires continuous skill acquisition and adaptation to new tasks while retaining prior knowledge. Dialogue State Tracking (DST), vital in these systems, often involves learning new services, confronting catastrophic forgetting and a critical capability loss termed the “Value Selection Quandary”. To address these challenges, we introduce the Reason-of-Select (RoS) distillation method by enhancing smaller models with a novel “meta-reasoning” capability. Meta-reasoning, employing an enhanced multi-domain perspective, combines fragments of meta-knowledge from domain-specific dialogues during continual learning, transcending traditional single-perspective reasoning. This domain bootstrapping process enhances the model’s ability to dissect intricate dialogues from multiple possible values, and its domain-agnostic property aligns data distribution across different domains, effectively mitigating forgetting. Besides, two novel improvements, “multi-value resolution” strategy and Semantic Contrastive Reasoning Selection method, significantly enhance RoS by generating DST-specific selection chains and mitigating hallucinations in teachers’ reasoning, ensuring effective and reliable knowledge transfer. Extensive experiments validate the exceptional performance and robust generalization capabilities of our method.</abstract>
    <identifier type="citekey">feng-etal-2024-continual</identifier>
    <identifier type="doi">10.18653/v1/2024.findings-acl.422</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-acl.422</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>7075</start>
            <end>7087</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Continual Dialogue State Tracking via Reason-of-Select Distillation
%A Feng, Yujie
%A Liu, Bo
%A Dong, Xiaoyu
%A Lu, Zexin
%A Zhan, Li-Ming
%A Wu, Xiao-Ming
%A Lam, Albert
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F feng-etal-2024-continual
%X An ideal dialogue system requires continuous skill acquisition and adaptation to new tasks while retaining prior knowledge. Dialogue State Tracking (DST), vital in these systems, often involves learning new services, confronting catastrophic forgetting and a critical capability loss termed the “Value Selection Quandary”. To address these challenges, we introduce the Reason-of-Select (RoS) distillation method by enhancing smaller models with a novel “meta-reasoning” capability. Meta-reasoning, employing an enhanced multi-domain perspective, combines fragments of meta-knowledge from domain-specific dialogues during continual learning, transcending traditional single-perspective reasoning. This domain bootstrapping process enhances the model’s ability to dissect intricate dialogues from multiple possible values, and its domain-agnostic property aligns data distribution across different domains, effectively mitigating forgetting. Besides, two novel improvements, “multi-value resolution” strategy and Semantic Contrastive Reasoning Selection method, significantly enhance RoS by generating DST-specific selection chains and mitigating hallucinations in teachers’ reasoning, ensuring effective and reliable knowledge transfer. Extensive experiments validate the exceptional performance and robust generalization capabilities of our method.
%R 10.18653/v1/2024.findings-acl.422
%U https://aclanthology.org/2024.findings-acl.422
%U https://doi.org/10.18653/v1/2024.findings-acl.422
%P 7075-7087

Markdown (Informal)

[Continual Dialogue State Tracking via Reason-of-Select Distillation](https://aclanthology.org/2024.findings-acl.422) (Feng et al., Findings 2024)

• Continual Dialogue State Tracking via Reason-of-Select Distillation (Feng et al., Findings 2024)

ACL

• Yujie Feng, Bo Liu, Xiaoyu Dong, Zexin Lu, Li-Ming Zhan, Xiao-Ming Wu, and Albert Lam. 2024. Continual Dialogue State Tracking via Reason-of-Select Distillation. In Findings of the Association for Computational Linguistics: ACL 2024, pages 7075–7087, Bangkok, Thailand. Association for Computational Linguistics.