<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="takayama-arase-2020-consistent">
    <titleInfo>
        <title>Consistent Response Generation with Controlled Specificity</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Junya</namePart>
        <namePart type="family">Takayama</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuki</namePart>
        <namePart type="family">Arase</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>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We propose a method to control the specificity of responses while maintaining the consistency with the utterances. We first design a metric based on pointwise mutual information, which measures the co-occurrence degree between an utterance and a response. To control the specificity of generated responses, we add the distant supervision based on the co-occurrence degree and a PMI-based word prediction mechanism to a sequence-to-sequence model. With these mechanisms, our model outputs the words with optimal specificity for a given specificity control variable. In experiments with open-domain dialogue corpora, automatic and human evaluation results confirm that our model controls the specificity of the response more sensitively than the conventional model and can generate highly consistent responses.</abstract>
    <identifier type="citekey">takayama-arase-2020-consistent</identifier>
    <identifier type="doi">10.18653/v1/2020.findings-emnlp.396</identifier>
    <location>
        <url>https://aclanthology.org/2020.findings-emnlp.396</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>4418</start>
            <end>4427</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Consistent Response Generation with Controlled Specificity
%A Takayama, Junya
%A Arase, Yuki
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F takayama-arase-2020-consistent
%X We propose a method to control the specificity of responses while maintaining the consistency with the utterances. We first design a metric based on pointwise mutual information, which measures the co-occurrence degree between an utterance and a response. To control the specificity of generated responses, we add the distant supervision based on the co-occurrence degree and a PMI-based word prediction mechanism to a sequence-to-sequence model. With these mechanisms, our model outputs the words with optimal specificity for a given specificity control variable. In experiments with open-domain dialogue corpora, automatic and human evaluation results confirm that our model controls the specificity of the response more sensitively than the conventional model and can generate highly consistent responses.
%R 10.18653/v1/2020.findings-emnlp.396
%U https://aclanthology.org/2020.findings-emnlp.396
%U https://doi.org/10.18653/v1/2020.findings-emnlp.396
%P 4418-4427

Markdown (Informal)

[Consistent Response Generation with Controlled Specificity](https://aclanthology.org/2020.findings-emnlp.396) (Takayama & Arase, Findings 2020)

• Consistent Response Generation with Controlled Specificity (Takayama & Arase, Findings 2020)

ACL

• Junya Takayama and Yuki Arase. 2020. Consistent Response Generation with Controlled Specificity. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4418–4427, Online. Association for Computational Linguistics.