<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qi-etal-2018-pre">
    <titleInfo>
        <title>When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ye</namePart>
        <namePart type="family">Qi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Devendra</namePart>
        <namePart type="family">Sachan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Matthieu</namePart>
        <namePart type="family">Felix</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sarguna</namePart>
        <namePart type="family">Padmanabhan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Graham</namePart>
        <namePart type="family">Neubig</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marilyn</namePart>
            <namePart type="family">Walker</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Heng</namePart>
            <namePart type="family">Ji</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Amanda</namePart>
            <namePart type="family">Stent</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">New Orleans, Louisiana</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The performance of Neural Machine Translation (NMT) systems often suffers in low-resource scenarios where sufficiently large-scale parallel corpora cannot be obtained. Pre-trained word embeddings have proven to be invaluable for improving performance in natural language analysis tasks, which often suffer from paucity of data. However, their utility for NMT has not been extensively explored. In this work, we perform five sets of experiments that analyze when we can expect pre-trained word embeddings to help in NMT tasks. We show that such embeddings can be surprisingly effective in some cases – providing gains of up to 20 BLEU points in the most favorable setting.</abstract>
    <identifier type="citekey">qi-etal-2018-pre</identifier>
    <identifier type="doi">10.18653/v1/N18-2084</identifier>
    <location>
        <url>https://aclanthology.org/N18-2084</url>
    </location>
    <part>
        <date>2018-06</date>
        <extent unit="page">
            <start>529</start>
            <end>535</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation?
%A Qi, Ye
%A Sachan, Devendra
%A Felix, Matthieu
%A Padmanabhan, Sarguna
%A Neubig, Graham
%Y Walker, Marilyn
%Y Ji, Heng
%Y Stent, Amanda
%S Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans, Louisiana
%F qi-etal-2018-pre
%X The performance of Neural Machine Translation (NMT) systems often suffers in low-resource scenarios where sufficiently large-scale parallel corpora cannot be obtained. Pre-trained word embeddings have proven to be invaluable for improving performance in natural language analysis tasks, which often suffer from paucity of data. However, their utility for NMT has not been extensively explored. In this work, we perform five sets of experiments that analyze when we can expect pre-trained word embeddings to help in NMT tasks. We show that such embeddings can be surprisingly effective in some cases – providing gains of up to 20 BLEU points in the most favorable setting.
%R 10.18653/v1/N18-2084
%U https://aclanthology.org/N18-2084
%U https://doi.org/10.18653/v1/N18-2084
%P 529-535

Markdown (Informal)

[When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation?](https://aclanthology.org/N18-2084) (Qi et al., NAACL 2018)

• When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation? (Qi et al., NAACL 2018)

ACL

• Ye Qi, Devendra Sachan, Matthieu Felix, Sarguna Padmanabhan, and Graham Neubig. 2018. When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation?. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 529–535, New Orleans, Louisiana. Association for Computational Linguistics.