<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoang-etal-2017-towards">
    <titleInfo>
        <title>Towards Decoding as Continuous Optimisation in Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Cong</namePart>
        <namePart type="given">Duy</namePart>
        <namePart type="given">Vu</namePart>
        <namePart type="family">Hoang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gholamreza</namePart>
        <namePart type="family">Haffari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Trevor</namePart>
        <namePart type="family">Cohn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Martha</namePart>
            <namePart type="family">Palmer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rebecca</namePart>
            <namePart type="family">Hwa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Riedel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Copenhagen, Denmark</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. We reformulate decoding, a discrete optimization problem, into a continuous problem, such that optimization can make use of efficient gradient-based techniques. Our powerful decoding framework allows for more accurate decoding for standard neural machine translation models, as well as enabling decoding in intractable models such as intersection of several different NMT models. Our empirical results show that our decoding framework is effective, and can leads to substantial improvements in translations, especially in situations where greedy search and beam search are not feasible. Finally, we show how the technique is highly competitive with, and complementary to, reranking.</abstract>
    <identifier type="citekey">hoang-etal-2017-towards</identifier>
    <identifier type="doi">10.18653/v1/D17-1014</identifier>
    <location>
        <url>https://aclanthology.org/D17-1014</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>146</start>
            <end>156</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Towards Decoding as Continuous Optimisation in Neural Machine Translation
%A Hoang, Cong Duy Vu
%A Haffari, Gholamreza
%A Cohn, Trevor
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F hoang-etal-2017-towards
%X We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. We reformulate decoding, a discrete optimization problem, into a continuous problem, such that optimization can make use of efficient gradient-based techniques. Our powerful decoding framework allows for more accurate decoding for standard neural machine translation models, as well as enabling decoding in intractable models such as intersection of several different NMT models. Our empirical results show that our decoding framework is effective, and can leads to substantial improvements in translations, especially in situations where greedy search and beam search are not feasible. Finally, we show how the technique is highly competitive with, and complementary to, reranking.
%R 10.18653/v1/D17-1014
%U https://aclanthology.org/D17-1014
%U https://doi.org/10.18653/v1/D17-1014
%P 146-156

Markdown (Informal)

[Towards Decoding as Continuous Optimisation in Neural Machine Translation](https://aclanthology.org/D17-1014) (Hoang et al., EMNLP 2017)

• Towards Decoding as Continuous Optimisation in Neural Machine Translation (Hoang et al., EMNLP 2017)

ACL

• Cong Duy Vu Hoang, Gholamreza Haffari, and Trevor Cohn. 2017. Towards Decoding as Continuous Optimisation in Neural Machine Translation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 146–156, Copenhagen, Denmark. Association for Computational Linguistics.