<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ohashi-higashinaka-2023-enhancing">
    <titleInfo>
        <title>Enhancing Task-oriented Dialogue Systems with Generative Post-processing Networks</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Atsumoto</namePart>
        <namePart type="family">Ohashi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ryuichiro</namePart>
        <namePart type="family">Higashinaka</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>Recently, post-processing networks (PPNs), which modify the outputs of arbitrary modules including non-differentiable ones in task-oriented dialogue systems, have been proposed. PPNs have successfully improved the dialogue performance by post-processing natural language understanding (NLU), dialogue state tracking (DST), and dialogue policy (Policy) modules with a classification-based approach. However, they cannot be applied to natural language generation (NLG) modules because the post-processing of the utterance output by the NLG module requires a generative approach. In this study, we propose a new post-processing component for NLG, generative post-processing networks (GenPPNs). For optimizing GenPPNs via reinforcement learning, the reward function incorporates dialogue act contribution, a new measure to evaluate the contribution of GenPPN-generated utterances with regard to task completion in dialogue. Through simulation and human evaluation experiments based on the MultiWOZ dataset, we confirmed that GenPPNs improve the task completion performance of task-oriented dialogue systems.</abstract>
    <identifier type="citekey">ohashi-higashinaka-2023-enhancing</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.231</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.231</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>3815</start>
            <end>3828</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Enhancing Task-oriented Dialogue Systems with Generative Post-processing Networks
%A Ohashi, Atsumoto
%A Higashinaka, Ryuichiro
%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 ohashi-higashinaka-2023-enhancing
%X Recently, post-processing networks (PPNs), which modify the outputs of arbitrary modules including non-differentiable ones in task-oriented dialogue systems, have been proposed. PPNs have successfully improved the dialogue performance by post-processing natural language understanding (NLU), dialogue state tracking (DST), and dialogue policy (Policy) modules with a classification-based approach. However, they cannot be applied to natural language generation (NLG) modules because the post-processing of the utterance output by the NLG module requires a generative approach. In this study, we propose a new post-processing component for NLG, generative post-processing networks (GenPPNs). For optimizing GenPPNs via reinforcement learning, the reward function incorporates dialogue act contribution, a new measure to evaluate the contribution of GenPPN-generated utterances with regard to task completion in dialogue. Through simulation and human evaluation experiments based on the MultiWOZ dataset, we confirmed that GenPPNs improve the task completion performance of task-oriented dialogue systems.
%R 10.18653/v1/2023.emnlp-main.231
%U https://aclanthology.org/2023.emnlp-main.231
%U https://doi.org/10.18653/v1/2023.emnlp-main.231
%P 3815-3828

Markdown (Informal)

[Enhancing Task-oriented Dialogue Systems with Generative Post-processing Networks](https://aclanthology.org/2023.emnlp-main.231) (Ohashi & Higashinaka, EMNLP 2023)

• Enhancing Task-oriented Dialogue Systems with Generative Post-processing Networks (Ohashi & Higashinaka, EMNLP 2023)

ACL

• Atsumoto Ohashi and Ryuichiro Higashinaka. 2023. Enhancing Task-oriented Dialogue Systems with Generative Post-processing Networks. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 3815–3828, Singapore. Association for Computational Linguistics.