<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-knight-2017-speeding">
    <titleInfo>
        <title>Speeding Up Neural Machine Translation Decoding by Shrinking Run-time Vocabulary</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xing</namePart>
        <namePart type="family">Shi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kevin</namePart>
        <namePart type="family">Knight</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Regina</namePart>
            <namePart type="family">Barzilay</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Min-Yen</namePart>
            <namePart type="family">Kan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vancouver, Canada</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We speed up Neural Machine Translation (NMT) decoding by shrinking run-time target vocabulary. We experiment with two shrinking approaches: Locality Sensitive Hashing (LSH) and word alignments. Using the latter method, we get a 2x overall speed-up over a highly-optimized GPU implementation, without hurting BLEU. On certain low-resource language pairs, the same methods improve BLEU by 0.5 points. We also report a negative result for LSH on GPUs, due to relatively large overhead, though it was successful on CPUs. Compared with Locality Sensitive Hashing (LSH), decoding with word alignments is GPU-friendly, orthogonal to existing speedup methods and more robust across language pairs.</abstract>
    <identifier type="citekey">shi-knight-2017-speeding</identifier>
    <identifier type="doi">10.18653/v1/P17-2091</identifier>
    <location>
        <url>https://aclanthology.org/P17-2091/</url>
    </location>
    <part>
        <date>2017-07</date>
        <extent unit="page">
            <start>574</start>
            <end>579</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Speeding Up Neural Machine Translation Decoding by Shrinking Run-time Vocabulary
%A Shi, Xing
%A Knight, Kevin
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F shi-knight-2017-speeding
%X We speed up Neural Machine Translation (NMT) decoding by shrinking run-time target vocabulary. We experiment with two shrinking approaches: Locality Sensitive Hashing (LSH) and word alignments. Using the latter method, we get a 2x overall speed-up over a highly-optimized GPU implementation, without hurting BLEU. On certain low-resource language pairs, the same methods improve BLEU by 0.5 points. We also report a negative result for LSH on GPUs, due to relatively large overhead, though it was successful on CPUs. Compared with Locality Sensitive Hashing (LSH), decoding with word alignments is GPU-friendly, orthogonal to existing speedup methods and more robust across language pairs.
%R 10.18653/v1/P17-2091
%U https://aclanthology.org/P17-2091/
%U https://doi.org/10.18653/v1/P17-2091
%P 574-579

Markdown (Informal)

[Speeding Up Neural Machine Translation Decoding by Shrinking Run-time Vocabulary](https://aclanthology.org/P17-2091/) (Shi & Knight, ACL 2017)

• Speeding Up Neural Machine Translation Decoding by Shrinking Run-time Vocabulary (Shi & Knight, ACL 2017)

ACL

• Xing Shi and Kevin Knight. 2017. Speeding Up Neural Machine Translation Decoding by Shrinking Run-time Vocabulary. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 574–579, Vancouver, Canada. Association for Computational Linguistics.