<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shapiro-duh-2018-morphological">
    <titleInfo>
        <title>Morphological Word Embeddings for Arabic Neural Machine Translation in Low-Resource Settings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pamela</namePart>
        <namePart type="family">Shapiro</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kevin</namePart>
        <namePart type="family">Duh</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 Second Workshop on Subword/Character LEvel Models</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Manaal</namePart>
            <namePart type="family">Faruqui</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hinrich</namePart>
            <namePart type="family">Schütze</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabel</namePart>
            <namePart type="family">Trancoso</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulia</namePart>
            <namePart type="family">Tsvetkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yadollah</namePart>
            <namePart type="family">Yaghoobzadeh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">New Orleans</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Neural machine translation has achieved impressive results in the last few years, but its success has been limited to settings with large amounts of parallel data. One way to improve NMT for lower-resource settings is to initialize a word-based NMT model with pretrained word embeddings. However, rare words still suffer from lower quality word embeddings when trained with standard word-level objectives. We introduce word embeddings that utilize morphological resources, and compare to purely unsupervised alternatives. We work with Arabic, a morphologically rich language with available linguistic resources, and perform Ar-to-En MT experiments on a small corpus of TED subtitles. We find that word embeddings utilizing subword information consistently outperform standard word embeddings on a word similarity task and as initialization of the source word embeddings in a low-resource NMT system.</abstract>
    <identifier type="citekey">shapiro-duh-2018-morphological</identifier>
    <identifier type="doi">10.18653/v1/W18-1201</identifier>
    <location>
        <url>https://aclanthology.org/W18-1201</url>
    </location>
    <part>
        <date>2018-06</date>
        <extent unit="page">
            <start>1</start>
            <end>11</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Morphological Word Embeddings for Arabic Neural Machine Translation in Low-Resource Settings
%A Shapiro, Pamela
%A Duh, Kevin
%Y Faruqui, Manaal
%Y Schütze, Hinrich
%Y Trancoso, Isabel
%Y Tsvetkov, Yulia
%Y Yaghoobzadeh, Yadollah
%S Proceedings of the Second Workshop on Subword/Character LEvel Models
%D 2018
%8 June
%I Association for Computational Linguistics
%C New Orleans
%F shapiro-duh-2018-morphological
%X Neural machine translation has achieved impressive results in the last few years, but its success has been limited to settings with large amounts of parallel data. One way to improve NMT for lower-resource settings is to initialize a word-based NMT model with pretrained word embeddings. However, rare words still suffer from lower quality word embeddings when trained with standard word-level objectives. We introduce word embeddings that utilize morphological resources, and compare to purely unsupervised alternatives. We work with Arabic, a morphologically rich language with available linguistic resources, and perform Ar-to-En MT experiments on a small corpus of TED subtitles. We find that word embeddings utilizing subword information consistently outperform standard word embeddings on a word similarity task and as initialization of the source word embeddings in a low-resource NMT system.
%R 10.18653/v1/W18-1201
%U https://aclanthology.org/W18-1201
%U https://doi.org/10.18653/v1/W18-1201
%P 1-11

Markdown (Informal)

[Morphological Word Embeddings for Arabic Neural Machine Translation in Low-Resource Settings](https://aclanthology.org/W18-1201) (Shapiro & Duh, SCLeM 2018)

• Morphological Word Embeddings for Arabic Neural Machine Translation in Low-Resource Settings (Shapiro & Duh, SCLeM 2018)

ACL

• Pamela Shapiro and Kevin Duh. 2018. Morphological Word Embeddings for Arabic Neural Machine Translation in Low-Resource Settings. In Proceedings of the Second Workshop on Subword/Character LEvel Models, pages 1–11, New Orleans. Association for Computational Linguistics.