<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kulikov-etal-2019-importance">
    <titleInfo>
        <title>Importance of Search and Evaluation Strategies in Neural Dialogue Modeling</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ilia</namePart>
        <namePart type="family">Kulikov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexander</namePart>
        <namePart type="family">Miller</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kyunghyun</namePart>
        <namePart type="family">Cho</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jason</namePart>
        <namePart type="family">Weston</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-oct–nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 12th International Conference on Natural Language Generation</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kees</namePart>
            <namePart type="family">van Deemter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chenghua</namePart>
            <namePart type="family">Lin</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hiroya</namePart>
            <namePart type="family">Takamura</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Tokyo, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We investigate the impact of search strategies in neural dialogue modeling. We first compare two standard search algorithms, greedy and beam search, as well as our newly proposed iterative beam search which produces a more diverse set of candidate responses. We evaluate these strategies in realistic full conversations with humans and propose a model-based Bayesian calibration to address annotator bias. These conversations are analyzed using two automatic metrics: log-probabilities assigned by the model and utterance diversity. Our experiments reveal that better search algorithms lead to higher rated conversations. However, finding the optimal selection mechanism to choose from a more diverse set of candidates is still an open question.</abstract>
    <identifier type="citekey">kulikov-etal-2019-importance</identifier>
    <identifier type="doi">10.18653/v1/W19-8609</identifier>
    <location>
        <url>https://aclanthology.org/W19-8609</url>
    </location>
    <part>
        <date>2019-oct–nov</date>
        <extent unit="page">
            <start>76</start>
            <end>87</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Importance of Search and Evaluation Strategies in Neural Dialogue Modeling
%A Kulikov, Ilia
%A Miller, Alexander
%A Cho, Kyunghyun
%A Weston, Jason
%Y van Deemter, Kees
%Y Lin, Chenghua
%Y Takamura, Hiroya
%S Proceedings of the 12th International Conference on Natural Language Generation
%D 2019
%8 oct–nov
%I Association for Computational Linguistics
%C Tokyo, Japan
%F kulikov-etal-2019-importance
%X We investigate the impact of search strategies in neural dialogue modeling. We first compare two standard search algorithms, greedy and beam search, as well as our newly proposed iterative beam search which produces a more diverse set of candidate responses. We evaluate these strategies in realistic full conversations with humans and propose a model-based Bayesian calibration to address annotator bias. These conversations are analyzed using two automatic metrics: log-probabilities assigned by the model and utterance diversity. Our experiments reveal that better search algorithms lead to higher rated conversations. However, finding the optimal selection mechanism to choose from a more diverse set of candidates is still an open question.
%R 10.18653/v1/W19-8609
%U https://aclanthology.org/W19-8609
%U https://doi.org/10.18653/v1/W19-8609
%P 76-87

Markdown (Informal)

[Importance of Search and Evaluation Strategies in Neural Dialogue Modeling](https://aclanthology.org/W19-8609) (Kulikov et al., INLG 2019)

• Importance of Search and Evaluation Strategies in Neural Dialogue Modeling (Kulikov et al., INLG 2019)

ACL

• Ilia Kulikov, Alexander Miller, Kyunghyun Cho, and Jason Weston. 2019. Importance of Search and Evaluation Strategies in Neural Dialogue Modeling. In Proceedings of the 12th International Conference on Natural Language Generation, pages 76–87, Tokyo, Japan. Association for Computational Linguistics.