<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shu-nakayama-2018-improving">
    <titleInfo>
        <title>Improving Beam Search by Removing Monotonic Constraint for Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Raphael</namePart>
        <namePart type="family">Shu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hideki</namePart>
        <namePart type="family">Nakayama</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Iryna</namePart>
            <namePart type="family">Gurevych</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yusuke</namePart>
            <namePart type="family">Miyao</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Melbourne, Australia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>To achieve high translation performance, neural machine translation models usually rely on the beam search algorithm for decoding sentences. The beam search finds good candidate translations by considering multiple hypotheses of translations simultaneously. However, as the algorithm produces hypotheses in a monotonic left-to-right order, a hypothesis can not be revisited once it is discarded. We found such monotonicity forces the algorithm to sacrifice some good decoding paths. To mitigate this problem, we relax the monotonic constraint of the beam search by maintaining all found hypotheses in a single priority queue and using a universal score function for hypothesis selection. The proposed algorithm allows discarded hypotheses to be recovered in a later step. Despite its simplicity, we show that the proposed decoding algorithm enhances the quality of selected hypotheses and improve the translations even for high-performance models in English-Japanese translation task.</abstract>
    <identifier type="citekey">shu-nakayama-2018-improving</identifier>
    <identifier type="doi">10.18653/v1/P18-2054</identifier>
    <location>
        <url>https://aclanthology.org/P18-2054</url>
    </location>
    <part>
        <date>2018-07</date>
        <extent unit="page">
            <start>339</start>
            <end>344</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Beam Search by Removing Monotonic Constraint for Neural Machine Translation
%A Shu, Raphael
%A Nakayama, Hideki
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F shu-nakayama-2018-improving
%X To achieve high translation performance, neural machine translation models usually rely on the beam search algorithm for decoding sentences. The beam search finds good candidate translations by considering multiple hypotheses of translations simultaneously. However, as the algorithm produces hypotheses in a monotonic left-to-right order, a hypothesis can not be revisited once it is discarded. We found such monotonicity forces the algorithm to sacrifice some good decoding paths. To mitigate this problem, we relax the monotonic constraint of the beam search by maintaining all found hypotheses in a single priority queue and using a universal score function for hypothesis selection. The proposed algorithm allows discarded hypotheses to be recovered in a later step. Despite its simplicity, we show that the proposed decoding algorithm enhances the quality of selected hypotheses and improve the translations even for high-performance models in English-Japanese translation task.
%R 10.18653/v1/P18-2054
%U https://aclanthology.org/P18-2054
%U https://doi.org/10.18653/v1/P18-2054
%P 339-344

Markdown (Informal)

[Improving Beam Search by Removing Monotonic Constraint for Neural Machine Translation](https://aclanthology.org/P18-2054) (Shu & Nakayama, ACL 2018)

• Improving Beam Search by Removing Monotonic Constraint for Neural Machine Translation (Shu & Nakayama, ACL 2018)

ACL

• Raphael Shu and Hideki Nakayama. 2018. Improving Beam Search by Removing Monotonic Constraint for Neural Machine Translation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 339–344, Melbourne, Australia. Association for Computational Linguistics.