<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miao-etal-2021-generative">
    <titleInfo>
        <title>A Generative Framework for Simultaneous Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yishu</namePart>
        <namePart type="family">Miao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Phil</namePart>
        <namePart type="family">Blunsom</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lucia</namePart>
        <namePart type="family">Specia</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We propose a generative framework for simultaneous machine translation. Conventional approaches use a fixed number of source words to translate or learn dynamic policies for the number of source words by reinforcement learning. Here we formulate simultaneous translation as a structural sequence-to-sequence learning problem. A latent variable is introduced to model read or translate actions at every time step, which is then integrated out to consider all the possible translation policies. A re-parameterised Poisson prior is used to regularise the policies which allows the model to explicitly balance translation quality and latency. The experiments demonstrate the effectiveness and robustness of the generative framework, which achieves the best BLEU scores given different average translation latencies on benchmark datasets.</abstract>
    <identifier type="citekey">miao-etal-2021-generative</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.536</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.536</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>6697</start>
            <end>6706</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Generative Framework for Simultaneous Machine Translation
%A Miao, Yishu
%A Blunsom, Phil
%A Specia, Lucia
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F miao-etal-2021-generative
%X We propose a generative framework for simultaneous machine translation. Conventional approaches use a fixed number of source words to translate or learn dynamic policies for the number of source words by reinforcement learning. Here we formulate simultaneous translation as a structural sequence-to-sequence learning problem. A latent variable is introduced to model read or translate actions at every time step, which is then integrated out to consider all the possible translation policies. A re-parameterised Poisson prior is used to regularise the policies which allows the model to explicitly balance translation quality and latency. The experiments demonstrate the effectiveness and robustness of the generative framework, which achieves the best BLEU scores given different average translation latencies on benchmark datasets.
%R 10.18653/v1/2021.emnlp-main.536
%U https://aclanthology.org/2021.emnlp-main.536
%U https://doi.org/10.18653/v1/2021.emnlp-main.536
%P 6697-6706

Markdown (Informal)

[A Generative Framework for Simultaneous Machine Translation](https://aclanthology.org/2021.emnlp-main.536) (Miao et al., EMNLP 2021)

• A Generative Framework for Simultaneous Machine Translation (Miao et al., EMNLP 2021)

ACL

• Yishu Miao, Phil Blunsom, and Lucia Specia. 2021. A Generative Framework for Simultaneous Machine Translation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6697–6706, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.