<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="azpiazu-pera-2020-hierarchical">
    <titleInfo>
        <title>Hierarchical Mapping for Crosslingual Word Embedding Alignment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ion</namePart>
        <namePart type="given">Madrazo</namePart>
        <namePart type="family">Azpiazu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Maria</namePart>
        <namePart type="given">Soledad</namePart>
        <namePart type="family">Pera</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>The alignment of word embedding spaces in different languages into a common crosslingual space has recently been in vogue. Strategies that do so compute pairwise alignments and then map multiple languages to a single pivot language (most often English). These strategies, however, are biased towards the choice of the pivot language, given that language proximity and the linguistic characteristics of the target language can strongly impact the resultant crosslingual space in detriment of topologically distant languages. We present a strategy that eliminates the need for a pivot language by learning the mappings across languages in a hierarchical way. Experiments demonstrate that our strategy significantly improves vocabulary induction scores in all existing benchmarks, as well as in a new non-English–centered benchmark we built, which we make publicly available.</abstract>
    <identifier type="citekey">azpiazu-pera-2020-hierarchical</identifier>
    <identifier type="doi">10.1162/tacl_a_00320</identifier>
    <location>
        <url>https://aclanthology.org/2020.tacl-1.24</url>
    </location>
    <part>
        <date>2020</date>
        <detail type="volume"><number>8</number></detail>
        <extent unit="page">
            <start>361</start>
            <end>376</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Hierarchical Mapping for Crosslingual Word Embedding Alignment
%A Azpiazu, Ion Madrazo
%A Pera, Maria Soledad
%J Transactions of the Association for Computational Linguistics
%D 2020
%V 8
%I MIT Press
%C Cambridge, MA
%F azpiazu-pera-2020-hierarchical
%X The alignment of word embedding spaces in different languages into a common crosslingual space has recently been in vogue. Strategies that do so compute pairwise alignments and then map multiple languages to a single pivot language (most often English). These strategies, however, are biased towards the choice of the pivot language, given that language proximity and the linguistic characteristics of the target language can strongly impact the resultant crosslingual space in detriment of topologically distant languages. We present a strategy that eliminates the need for a pivot language by learning the mappings across languages in a hierarchical way. Experiments demonstrate that our strategy significantly improves vocabulary induction scores in all existing benchmarks, as well as in a new non-English–centered benchmark we built, which we make publicly available.
%R 10.1162/tacl_a_00320
%U https://aclanthology.org/2020.tacl-1.24
%U https://doi.org/10.1162/tacl_a_00320
%P 361-376

Markdown (Informal)

[Hierarchical Mapping for Crosslingual Word Embedding Alignment](https://aclanthology.org/2020.tacl-1.24) (Azpiazu & Pera, TACL 2020)

• Hierarchical Mapping for Crosslingual Word Embedding Alignment (Azpiazu & Pera, TACL 2020)

ACL

• Ion Madrazo Azpiazu and Maria Soledad Pera. 2020. Hierarchical Mapping for Crosslingual Word Embedding Alignment. Transactions of the Association for Computational Linguistics, 8:361–376.