<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="demasi-etal-2020-multi">
    <titleInfo>
        <title>A Multi-Persona Chatbot for Hotline Counselor Training</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Orianna</namePart>
        <namePart type="family">Demasi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yu</namePart>
        <namePart type="family">Li</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>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Suicide prevention hotline counselors aid individuals during difficult times through millions of calls and chats. A chatbot cannot safely replace a counselor, but we explore whether a chatbot can be developed to help train human counselors. Such a system needs to simulate intimate situations across multiple practice sessions. Open-domain dialogue systems frequently suffer from generic responses that do not characterize personal stories, so we look to infuse conversations with persona information by mimicking prototype conversations. Towards building a “Crisisbot” hotline visitor simulation, we propose a counseling strategy annotation scheme and a multi-task framework that leverages these counselor strategies to retrieve similar examples, generate diverse sub-utterances, and interleave prototype and generated sub-utterances into complex responses. We evaluate this framework with crowdworkers and experienced hotline counselors. The framework considerably increases response diversity and specificity, with limited impact to coherence. Our results also show a considerable discrepancy between crowdworker and counselor judgements, which emphasizes the importance of including target populations in system development and evaluation.</abstract>
    <identifier type="citekey">demasi-etal-2020-multi</identifier>
    <identifier type="doi">10.18653/v1/2020.findings-emnlp.324</identifier>
    <location>
        <url>https://aclanthology.org/2020.findings-emnlp.324</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>3623</start>
            <end>3636</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Multi-Persona Chatbot for Hotline Counselor Training
%A Demasi, Orianna
%A Li, Yu
%A Yu, Zhou
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F demasi-etal-2020-multi
%X Suicide prevention hotline counselors aid individuals during difficult times through millions of calls and chats. A chatbot cannot safely replace a counselor, but we explore whether a chatbot can be developed to help train human counselors. Such a system needs to simulate intimate situations across multiple practice sessions. Open-domain dialogue systems frequently suffer from generic responses that do not characterize personal stories, so we look to infuse conversations with persona information by mimicking prototype conversations. Towards building a “Crisisbot” hotline visitor simulation, we propose a counseling strategy annotation scheme and a multi-task framework that leverages these counselor strategies to retrieve similar examples, generate diverse sub-utterances, and interleave prototype and generated sub-utterances into complex responses. We evaluate this framework with crowdworkers and experienced hotline counselors. The framework considerably increases response diversity and specificity, with limited impact to coherence. Our results also show a considerable discrepancy between crowdworker and counselor judgements, which emphasizes the importance of including target populations in system development and evaluation.
%R 10.18653/v1/2020.findings-emnlp.324
%U https://aclanthology.org/2020.findings-emnlp.324
%U https://doi.org/10.18653/v1/2020.findings-emnlp.324
%P 3623-3636

Markdown (Informal)

[A Multi-Persona Chatbot for Hotline Counselor Training](https://aclanthology.org/2020.findings-emnlp.324) (Demasi et al., Findings 2020)

• A Multi-Persona Chatbot for Hotline Counselor Training (Demasi et al., Findings 2020)

ACL

• Orianna Demasi, Yu Li, and Zhou Yu. 2020. A Multi-Persona Chatbot for Hotline Counselor Training. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3623–3636, Online. Association for Computational Linguistics.