<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ormazabal-etal-2019-analyzing">
    <titleInfo>
        <title>Analyzing the Limitations of Cross-lingual Word Embedding Mappings</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Aitor</namePart>
        <namePart type="family">Ormazabal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mikel</namePart>
        <namePart type="family">Artetxe</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gorka</namePart>
        <namePart type="family">Labaka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aitor</namePart>
        <namePart type="family">Soroa</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eneko</namePart>
        <namePart type="family">Agirre</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Recent research in cross-lingual word embeddings has almost exclusively focused on offline methods, which independently train word embeddings in different languages and map them to a shared space through linear transformations. While several authors have questioned the underlying isomorphism assumption, which states that word embeddings in different languages have approximately the same structure, it is not clear whether this is an inherent limitation of mapping approaches or a more general issue when learning cross-lingual embeddings. So as to answer this question, we experiment with parallel corpora, which allows us to compare offline mapping to an extension of skip-gram that jointly learns both embedding spaces. We observe that, under these ideal conditions, joint learning yields to more isomorphic embeddings, is less sensitive to hubness, and obtains stronger results in bilingual lexicon induction. We thus conclude that current mapping methods do have strong limitations, calling for further research to jointly learn cross-lingual embeddings with a weaker cross-lingual signal.</abstract>
    <identifier type="citekey">ormazabal-etal-2019-analyzing</identifier>
    <identifier type="doi">10.18653/v1/P19-1492</identifier>
    <location>
        <url>https://aclanthology.org/P19-1492</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>4990</start>
            <end>4995</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Analyzing the Limitations of Cross-lingual Word Embedding Mappings
%A Ormazabal, Aitor
%A Artetxe, Mikel
%A Labaka, Gorka
%A Soroa, Aitor
%A Agirre, Eneko
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F ormazabal-etal-2019-analyzing
%X Recent research in cross-lingual word embeddings has almost exclusively focused on offline methods, which independently train word embeddings in different languages and map them to a shared space through linear transformations. While several authors have questioned the underlying isomorphism assumption, which states that word embeddings in different languages have approximately the same structure, it is not clear whether this is an inherent limitation of mapping approaches or a more general issue when learning cross-lingual embeddings. So as to answer this question, we experiment with parallel corpora, which allows us to compare offline mapping to an extension of skip-gram that jointly learns both embedding spaces. We observe that, under these ideal conditions, joint learning yields to more isomorphic embeddings, is less sensitive to hubness, and obtains stronger results in bilingual lexicon induction. We thus conclude that current mapping methods do have strong limitations, calling for further research to jointly learn cross-lingual embeddings with a weaker cross-lingual signal.
%R 10.18653/v1/P19-1492
%U https://aclanthology.org/P19-1492
%U https://doi.org/10.18653/v1/P19-1492
%P 4990-4995

Markdown (Informal)

[Analyzing the Limitations of Cross-lingual Word Embedding Mappings](https://aclanthology.org/P19-1492) (Ormazabal et al., ACL 2019)

• Analyzing the Limitations of Cross-lingual Word Embedding Mappings (Ormazabal et al., ACL 2019)

ACL

• Aitor Ormazabal, Mikel Artetxe, Gorka Labaka, Aitor Soroa, and Eneko Agirre. 2019. Analyzing the Limitations of Cross-lingual Word Embedding Mappings. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4990–4995, Florence, Italy. Association for Computational Linguistics.