<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bahar-etal-2018-towards">
    <titleInfo>
        <title>Towards Two-Dimensional Sequence to Sequence Model in Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Parnia</namePart>
        <namePart type="family">Bahar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christopher</namePart>
        <namePart type="family">Brix</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hermann</namePart>
        <namePart type="family">Ney</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-oct-nov</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ellen</namePart>
            <namePart type="family">Riloff</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Chiang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Julia</namePart>
            <namePart type="family">Hockenmaier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jun’ichi</namePart>
            <namePart type="family">Tsujii</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Brussels, Belgium</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This work investigates an alternative model for neural machine translation (NMT) and proposes a novel architecture, where we employ a multi-dimensional long short-term memory (MDLSTM) for translation modelling. In the state-of-the-art methods, source and target sentences are treated as one-dimensional sequences over time, while we view translation as a two-dimensional (2D) mapping using an MDLSTM layer to define the correspondence between source and target words. We extend beyond the current sequence to sequence backbone NMT models to a 2D structure in which the source and target sentences are aligned with each other in a 2D grid. Our proposed topology shows consistent improvements over attention-based sequence to sequence model on two WMT 2017 tasks, German\textless-\textgreaterEnglish.</abstract>
    <identifier type="citekey">bahar-etal-2018-towards</identifier>
    <identifier type="doi">10.18653/v1/D18-1335</identifier>
    <location>
        <url>https://aclanthology.org/D18-1335</url>
    </location>
    <part>
        <date>2018-oct-nov</date>
        <extent unit="page">
            <start>3009</start>
            <end>3015</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Towards Two-Dimensional Sequence to Sequence Model in Neural Machine Translation
%A Bahar, Parnia
%A Brix, Christopher
%A Ney, Hermann
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F bahar-etal-2018-towards
%X This work investigates an alternative model for neural machine translation (NMT) and proposes a novel architecture, where we employ a multi-dimensional long short-term memory (MDLSTM) for translation modelling. In the state-of-the-art methods, source and target sentences are treated as one-dimensional sequences over time, while we view translation as a two-dimensional (2D) mapping using an MDLSTM layer to define the correspondence between source and target words. We extend beyond the current sequence to sequence backbone NMT models to a 2D structure in which the source and target sentences are aligned with each other in a 2D grid. Our proposed topology shows consistent improvements over attention-based sequence to sequence model on two WMT 2017 tasks, German\textless-\textgreaterEnglish.
%R 10.18653/v1/D18-1335
%U https://aclanthology.org/D18-1335
%U https://doi.org/10.18653/v1/D18-1335
%P 3009-3015

Markdown (Informal)

[Towards Two-Dimensional Sequence to Sequence Model in Neural Machine Translation](https://aclanthology.org/D18-1335) (Bahar et al., EMNLP 2018)

• Towards Two-Dimensional Sequence to Sequence Model in Neural Machine Translation (Bahar et al., EMNLP 2018)

ACL

• Parnia Bahar, Christopher Brix, and Hermann Ney. 2018. Towards Two-Dimensional Sequence to Sequence Model in Neural Machine Translation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3009–3015, Brussels, Belgium. Association for Computational Linguistics.