@inproceedings{glavas-etal-2019-properly,
title = "How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions",
author = "Glava{\v{s}}, Goran and
Litschko, Robert and
Ruder, Sebastian and
Vuli{\'c}, Ivan",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1070",
doi = "10.18653/v1/P19-1070",
pages = "710--721",
abstract = "Cross-lingual word embeddings (CLEs) facilitate cross-lingual transfer of NLP models. Despite their ubiquitous downstream usage, increasingly popular projection-based CLE models are almost exclusively evaluated on bilingual lexicon induction (BLI). Even the BLI evaluations vary greatly, hindering our ability to correctly interpret performance and properties of different CLE models. In this work, we take the first step towards a comprehensive evaluation of CLE models: we thoroughly evaluate both supervised and unsupervised CLE models, for a large number of language pairs, on BLI and three downstream tasks, providing new insights concerning the ability of cutting-edge CLE models to support cross-lingual NLP. We empirically demonstrate that the performance of CLE models largely depends on the task at hand and that optimizing CLE models for BLI may hurt downstream performance. We indicate the most robust supervised and unsupervised CLE models and emphasize the need to reassess simple baselines, which still display competitive performance across the board. We hope our work catalyzes further research on CLE evaluation and model analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="glavas-etal-2019-properly">
<titleInfo>
<title>How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Glavaš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Litschko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</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>Cross-lingual word embeddings (CLEs) facilitate cross-lingual transfer of NLP models. Despite their ubiquitous downstream usage, increasingly popular projection-based CLE models are almost exclusively evaluated on bilingual lexicon induction (BLI). Even the BLI evaluations vary greatly, hindering our ability to correctly interpret performance and properties of different CLE models. In this work, we take the first step towards a comprehensive evaluation of CLE models: we thoroughly evaluate both supervised and unsupervised CLE models, for a large number of language pairs, on BLI and three downstream tasks, providing new insights concerning the ability of cutting-edge CLE models to support cross-lingual NLP. We empirically demonstrate that the performance of CLE models largely depends on the task at hand and that optimizing CLE models for BLI may hurt downstream performance. We indicate the most robust supervised and unsupervised CLE models and emphasize the need to reassess simple baselines, which still display competitive performance across the board. We hope our work catalyzes further research on CLE evaluation and model analysis.</abstract>
<identifier type="citekey">glavas-etal-2019-properly</identifier>
<identifier type="doi">10.18653/v1/P19-1070</identifier>
<location>
<url>https://aclanthology.org/P19-1070</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>710</start>
<end>721</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions
%A Glavaš, Goran
%A Litschko, Robert
%A Ruder, Sebastian
%A Vulić, Ivan
%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 glavas-etal-2019-properly
%X Cross-lingual word embeddings (CLEs) facilitate cross-lingual transfer of NLP models. Despite their ubiquitous downstream usage, increasingly popular projection-based CLE models are almost exclusively evaluated on bilingual lexicon induction (BLI). Even the BLI evaluations vary greatly, hindering our ability to correctly interpret performance and properties of different CLE models. In this work, we take the first step towards a comprehensive evaluation of CLE models: we thoroughly evaluate both supervised and unsupervised CLE models, for a large number of language pairs, on BLI and three downstream tasks, providing new insights concerning the ability of cutting-edge CLE models to support cross-lingual NLP. We empirically demonstrate that the performance of CLE models largely depends on the task at hand and that optimizing CLE models for BLI may hurt downstream performance. We indicate the most robust supervised and unsupervised CLE models and emphasize the need to reassess simple baselines, which still display competitive performance across the board. We hope our work catalyzes further research on CLE evaluation and model analysis.
%R 10.18653/v1/P19-1070
%U https://aclanthology.org/P19-1070
%U https://doi.org/10.18653/v1/P19-1070
%P 710-721
Markdown (Informal)
[How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions](https://aclanthology.org/P19-1070) (Glavaš et al., ACL 2019)
ACL