<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-etal-2023-retrieval">
    <titleInfo>
        <title>Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Weizhou</namePart>
        <namePart type="family">Shen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yingqi</namePart>
        <namePart type="family">Gao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Canbin</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fanqi</namePart>
        <namePart type="family">Wan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaojun</namePart>
        <namePart type="family">Quan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Bi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Developing an efficient retriever to retrieve knowledge from a large-scale knowledge base (KB) is critical for task-oriented dialogue systems to effectively handle localized and specialized tasks. However, widely used generative models such as T5 and ChatGPT often struggle to differentiate subtle differences among the retrieved KB records when generating responses, resulting in suboptimal quality of generated responses. In this paper, we propose the application of maximal marginal likelihood to train a perceptive retriever by utilizing signals from response generation for supervision. In addition, our approach goes beyond considering solely retrieved entities and incorporates various meta knowledge to guide the generator, thus improving the utilization of knowledge. We evaluate our approach on three task-oriented dialogue datasets using T5 and ChatGPT as the backbone models. The results demonstrate that when combined with meta knowledge, the response generator can effectively leverage high-quality knowledge records from the retriever and enhance the quality of generated responses. The code of this work is available at https://github.com/shenwzh3/MK-TOD.</abstract>
    <identifier type="citekey">shen-etal-2023-retrieval</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.514</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.514</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>8261</start>
            <end>8275</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System
%A Shen, Weizhou
%A Gao, Yingqi
%A Huang, Canbin
%A Wan, Fanqi
%A Quan, Xiaojun
%A Bi, Wei
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F shen-etal-2023-retrieval
%X Developing an efficient retriever to retrieve knowledge from a large-scale knowledge base (KB) is critical for task-oriented dialogue systems to effectively handle localized and specialized tasks. However, widely used generative models such as T5 and ChatGPT often struggle to differentiate subtle differences among the retrieved KB records when generating responses, resulting in suboptimal quality of generated responses. In this paper, we propose the application of maximal marginal likelihood to train a perceptive retriever by utilizing signals from response generation for supervision. In addition, our approach goes beyond considering solely retrieved entities and incorporates various meta knowledge to guide the generator, thus improving the utilization of knowledge. We evaluate our approach on three task-oriented dialogue datasets using T5 and ChatGPT as the backbone models. The results demonstrate that when combined with meta knowledge, the response generator can effectively leverage high-quality knowledge records from the retriever and enhance the quality of generated responses. The code of this work is available at https://github.com/shenwzh3/MK-TOD.
%R 10.18653/v1/2023.emnlp-main.514
%U https://aclanthology.org/2023.emnlp-main.514
%U https://doi.org/10.18653/v1/2023.emnlp-main.514
%P 8261-8275

Markdown (Informal)

[Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System](https://aclanthology.org/2023.emnlp-main.514) (Shen et al., EMNLP 2023)

• Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System (Shen et al., EMNLP 2023)

ACL

• Weizhou Shen, Yingqi Gao, Canbin Huang, Fanqi Wan, Xiaojun Quan, and Wei Bi. 2023. Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8261–8275, Singapore. Association for Computational Linguistics.