<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="levy-etal-2017-strong">
    <titleInfo>
        <title>A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Omer</namePart>
        <namePart type="family">Levy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anders</namePart>
        <namePart type="family">Søgaard</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yoav</namePart>
        <namePart type="family">Goldberg</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Mirella</namePart>
            <namePart type="family">Lapata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Phil</namePart>
            <namePart type="family">Blunsom</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alexander</namePart>
            <namePart type="family">Koller</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Valencia, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>While cross-lingual word embeddings have been studied extensively in recent years, the qualitative differences between the different algorithms remain vague. We observe that whether or not an algorithm uses a particular feature set (sentence IDs) accounts for a significant performance gap among these algorithms. This feature set is also used by traditional alignment algorithms, such as IBM Model-1, which demonstrate similar performance to state-of-the-art embedding algorithms on a variety of benchmarks. Overall, we observe that different algorithmic approaches for utilizing the sentence ID feature space result in similar performance. This paper draws both empirical and theoretical parallels between the embedding and alignment literature, and suggests that adding additional sources of information, which go beyond the traditional signal of bilingual sentence-aligned corpora, may substantially improve cross-lingual word embeddings, and that future baselines should at least take such features into account.</abstract>
    <identifier type="citekey">levy-etal-2017-strong</identifier>
    <location>
        <url>https://aclanthology.org/E17-1072</url>
    </location>
    <part>
        <date>2017-04</date>
        <extent unit="page">
            <start>765</start>
            <end>774</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments
%A Levy, Omer
%A Søgaard, Anders
%A Goldberg, Yoav
%Y Lapata, Mirella
%Y Blunsom, Phil
%Y Koller, Alexander
%S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F levy-etal-2017-strong
%X While cross-lingual word embeddings have been studied extensively in recent years, the qualitative differences between the different algorithms remain vague. We observe that whether or not an algorithm uses a particular feature set (sentence IDs) accounts for a significant performance gap among these algorithms. This feature set is also used by traditional alignment algorithms, such as IBM Model-1, which demonstrate similar performance to state-of-the-art embedding algorithms on a variety of benchmarks. Overall, we observe that different algorithmic approaches for utilizing the sentence ID feature space result in similar performance. This paper draws both empirical and theoretical parallels between the embedding and alignment literature, and suggests that adding additional sources of information, which go beyond the traditional signal of bilingual sentence-aligned corpora, may substantially improve cross-lingual word embeddings, and that future baselines should at least take such features into account.
%U https://aclanthology.org/E17-1072
%P 765-774

Markdown (Informal)

[A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments](https://aclanthology.org/E17-1072) (Levy et al., EACL 2017)

• A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments (Levy et al., EACL 2017)

ACL

• Omer Levy, Anders Søgaard, and Yoav Goldberg. 2017. A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 765–774, Valencia, Spain. Association for Computational Linguistics.