<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marchisio-etal-2022-isovec">
    <titleInfo>
        <title>IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kelly</namePart>
        <namePart type="family">Marchisio</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Neha</namePart>
        <namePart type="family">Verma</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>
    <name type="personal">
        <namePart type="given">Philipp</namePart>
        <namePart type="family">Koehn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yoav</namePart>
            <namePart type="family">Goldberg</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zornitsa</namePart>
            <namePart type="family">Kozareva</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yue</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The ability to extract high-quality translation dictionaries from monolingual word embedding spaces depends critically on the geometric similarity of the spaces—their degree of “isomorphism.” We address the root-cause of faulty cross-lingual mapping: that word embedding training resulted in the underlying spaces being non-isomorphic. We incorporate global measures of isomorphism directly into the skipgram loss function, successfully increasing the relative isomorphism of trained word embedding spaces and improving their ability to be mapped to a shared cross-lingual space. The result is improved bilingual lexicon induction in general data conditions, under domain mismatch, and with training algorithm dissimilarities. We release IsoVec at https://github.com/kellymarchisio/isovec.</abstract>
    <identifier type="citekey">marchisio-etal-2022-isovec</identifier>
    <identifier type="doi">10.18653/v1/2022.emnlp-main.404</identifier>
    <location>
        <url>https://aclanthology.org/2022.emnlp-main.404</url>
    </location>
    <part>
        <date>2022-12</date>
        <extent unit="page">
            <start>6019</start>
            <end>6033</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces
%A Marchisio, Kelly
%A Verma, Neha
%A Duh, Kevin
%A Koehn, Philipp
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F marchisio-etal-2022-isovec
%X The ability to extract high-quality translation dictionaries from monolingual word embedding spaces depends critically on the geometric similarity of the spaces—their degree of “isomorphism.” We address the root-cause of faulty cross-lingual mapping: that word embedding training resulted in the underlying spaces being non-isomorphic. We incorporate global measures of isomorphism directly into the skipgram loss function, successfully increasing the relative isomorphism of trained word embedding spaces and improving their ability to be mapped to a shared cross-lingual space. The result is improved bilingual lexicon induction in general data conditions, under domain mismatch, and with training algorithm dissimilarities. We release IsoVec at https://github.com/kellymarchisio/isovec.
%R 10.18653/v1/2022.emnlp-main.404
%U https://aclanthology.org/2022.emnlp-main.404
%U https://doi.org/10.18653/v1/2022.emnlp-main.404
%P 6019-6033

Markdown (Informal)

[IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces](https://aclanthology.org/2022.emnlp-main.404) (Marchisio et al., EMNLP 2022)

• IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces (Marchisio et al., EMNLP 2022)

ACL

• Kelly Marchisio, Neha Verma, Kevin Duh, and Philipp Koehn. 2022. IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6019–6033, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.