<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ippolito-etal-2019-comparison">
    <titleInfo>
        <title>Comparison of Diverse Decoding Methods from Conditional Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Daphne</namePart>
        <namePart type="family">Ippolito</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Reno</namePart>
        <namePart type="family">Kriz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">João</namePart>
        <namePart type="family">Sedoc</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maria</namePart>
        <namePart type="family">Kustikova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chris</namePart>
        <namePart type="family">Callison-Burch</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>While conditional language models have greatly improved in their ability to output high quality natural language, many NLP applications benefit from being able to generate a diverse set of candidate sequences. Diverse decoding strategies aim to, within a given-sized candidate list, cover as much of the space of high-quality outputs as possible, leading to improvements for tasks that rerank and combine candidate outputs. Standard decoding methods, such as beam search, optimize for generating high likelihood sequences rather than diverse ones, though recent work has focused on increasing diversity in these methods. In this work, we perform an extensive survey of decoding-time strategies for generating diverse outputs from a conditional language model. In addition, we present a novel method where we over-sample candidates, then use clustering to remove similar sequences, thus achieving high diversity without sacrificing quality.</abstract>
    <identifier type="citekey">ippolito-etal-2019-comparison</identifier>
    <identifier type="doi">10.18653/v1/P19-1365</identifier>
    <location>
        <url>https://aclanthology.org/P19-1365</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>3752</start>
            <end>3762</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Comparison of Diverse Decoding Methods from Conditional Language Models
%A Ippolito, Daphne
%A Kriz, Reno
%A Sedoc, João
%A Kustikova, Maria
%A Callison-Burch, Chris
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F ippolito-etal-2019-comparison
%X While conditional language models have greatly improved in their ability to output high quality natural language, many NLP applications benefit from being able to generate a diverse set of candidate sequences. Diverse decoding strategies aim to, within a given-sized candidate list, cover as much of the space of high-quality outputs as possible, leading to improvements for tasks that rerank and combine candidate outputs. Standard decoding methods, such as beam search, optimize for generating high likelihood sequences rather than diverse ones, though recent work has focused on increasing diversity in these methods. In this work, we perform an extensive survey of decoding-time strategies for generating diverse outputs from a conditional language model. In addition, we present a novel method where we over-sample candidates, then use clustering to remove similar sequences, thus achieving high diversity without sacrificing quality.
%R 10.18653/v1/P19-1365
%U https://aclanthology.org/P19-1365
%U https://doi.org/10.18653/v1/P19-1365
%P 3752-3762

Markdown (Informal)

[Comparison of Diverse Decoding Methods from Conditional Language Models](https://aclanthology.org/P19-1365) (Ippolito et al., ACL 2019)

• Comparison of Diverse Decoding Methods from Conditional Language Models (Ippolito et al., ACL 2019)

ACL

• Daphne Ippolito, Reno Kriz, João Sedoc, Maria Kustikova, and Chris Callison-Burch. 2019. Comparison of Diverse Decoding Methods from Conditional Language Models. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3752–3762, Florence, Italy. Association for Computational Linguistics.