<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bae-etal-2022-building">
    <titleInfo>
        <title>Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sanghwan</namePart>
        <namePart type="family">Bae</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Donghyun</namePart>
        <namePart type="family">Kwak</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sungdong</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Donghoon</namePart>
        <namePart type="family">Ham</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Soyoung</namePart>
        <namePart type="family">Kang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sang-Woo</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Woomyoung</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marine</namePart>
            <namePart type="family">Carpuat</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marie-Catherine</namePart>
            <namePart type="family">de Marneffe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ivan</namePart>
            <namePart type="given">Vladimir</namePart>
            <namePart type="family">Meza Ruiz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Seattle, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent open-domain dialogue models have brought numerous breakthroughs. However, building a chat system is not scalable since it often requires a considerable volume of human-human dialogue data, especially when enforcing features such as persona, style, or safety. In this work, we study the challenge of imposing roles on open-domain dialogue systems, with the goal of making the systems maintain consistent roles while conversing naturally with humans. To accomplish this, the system must satisfy a role specification that includes certain conditions on the stated features as well as a system policy on whether or not certain types of utterances are allowed. For this, we propose an efficient data collection framework leveraging in-context few-shot learning of large-scale language models for building role-satisfying dialogue dataset from scratch. We then compare various architectures for open-domain dialogue systems in terms of meeting role specifications while maintaining conversational abilities. Automatic and human evaluations show that our models return few out-of-bounds utterances, keeping competitive performance on general metrics. We release a Korean dialogue dataset we built for further research.</abstract>
    <identifier type="citekey">bae-etal-2022-building</identifier>
    <identifier type="doi">10.18653/v1/2022.naacl-main.155</identifier>
    <location>
        <url>https://aclanthology.org/2022.naacl-main.155</url>
    </location>
    <part>
        <date>2022-07</date>
        <extent unit="page">
            <start>2128</start>
            <end>2150</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models
%A Bae, Sanghwan
%A Kwak, Donghyun
%A Kim, Sungdong
%A Ham, Donghoon
%A Kang, Soyoung
%A Lee, Sang-Woo
%A Park, Woomyoung
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F bae-etal-2022-building
%X Recent open-domain dialogue models have brought numerous breakthroughs. However, building a chat system is not scalable since it often requires a considerable volume of human-human dialogue data, especially when enforcing features such as persona, style, or safety. In this work, we study the challenge of imposing roles on open-domain dialogue systems, with the goal of making the systems maintain consistent roles while conversing naturally with humans. To accomplish this, the system must satisfy a role specification that includes certain conditions on the stated features as well as a system policy on whether or not certain types of utterances are allowed. For this, we propose an efficient data collection framework leveraging in-context few-shot learning of large-scale language models for building role-satisfying dialogue dataset from scratch. We then compare various architectures for open-domain dialogue systems in terms of meeting role specifications while maintaining conversational abilities. Automatic and human evaluations show that our models return few out-of-bounds utterances, keeping competitive performance on general metrics. We release a Korean dialogue dataset we built for further research.
%R 10.18653/v1/2022.naacl-main.155
%U https://aclanthology.org/2022.naacl-main.155
%U https://doi.org/10.18653/v1/2022.naacl-main.155
%P 2128-2150

Markdown (Informal)

[Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models](https://aclanthology.org/2022.naacl-main.155) (Bae et al., NAACL 2022)

• Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models (Bae et al., NAACL 2022)

ACL

• Sanghwan Bae, Donghyun Kwak, Sungdong Kim, Donghoon Ham, Soyoung Kang, Sang-Woo Lee, and Woomyoung Park. 2022. Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2128–2150, Seattle, United States. Association for Computational Linguistics.