@inproceedings{vulic-etal-2020-improving,
title = "Improving Bilingual Lexicon Induction with Unsupervised Post-Processing of Monolingual Word Vector Spaces",
author = "Vuli{\'c}, Ivan and
Korhonen, Anna and
Glava{\v{s}}, Goran",
editor = "Gella, Spandana and
Welbl, Johannes and
Rei, Marek and
Petroni, Fabio and
Lewis, Patrick and
Strubell, Emma and
Seo, Minjoon and
Hajishirzi, Hannaneh",
booktitle = "Proceedings of the 5th Workshop on Representation Learning for NLP",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.repl4nlp-1.7",
doi = "10.18653/v1/2020.repl4nlp-1.7",
pages = "45--54",
abstract = "Work on projection-based induction of cross-lingual word embedding spaces (CLWEs) predominantly focuses on the improvement of the projection (i.e., mapping) mechanisms. In this work, in contrast, we show that a simple method for post-processing monolingual embedding spaces facilitates learning of the cross-lingual alignment and, in turn, substantially improves bilingual lexicon induction (BLI). The post-processing method we examine is grounded in the generalisation of first- and second-order monolingual similarities to the nth-order similarity. By post-processing monolingual spaces before the cross-lingual alignment, the method can be coupled with any projection-based method for inducing CLWE spaces. We demonstrate the effectiveness of this simple monolingual post-processing across a set of 15 typologically diverse languages (i.e., 15*14 BLI setups), and in combination with two different projection methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vulic-etal-2020-improving">
<titleInfo>
<title>Improving Bilingual Lexicon Induction with Unsupervised Post-Processing of Monolingual Word Vector Spaces</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Glavaš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Representation Learning for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Welbl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Rei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Petroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emma</namePart>
<namePart type="family">Strubell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjoon</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannaneh</namePart>
<namePart type="family">Hajishirzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Work on projection-based induction of cross-lingual word embedding spaces (CLWEs) predominantly focuses on the improvement of the projection (i.e., mapping) mechanisms. In this work, in contrast, we show that a simple method for post-processing monolingual embedding spaces facilitates learning of the cross-lingual alignment and, in turn, substantially improves bilingual lexicon induction (BLI). The post-processing method we examine is grounded in the generalisation of first- and second-order monolingual similarities to the nth-order similarity. By post-processing monolingual spaces before the cross-lingual alignment, the method can be coupled with any projection-based method for inducing CLWE spaces. We demonstrate the effectiveness of this simple monolingual post-processing across a set of 15 typologically diverse languages (i.e., 15*14 BLI setups), and in combination with two different projection methods.</abstract>
<identifier type="citekey">vulic-etal-2020-improving</identifier>
<identifier type="doi">10.18653/v1/2020.repl4nlp-1.7</identifier>
<location>
<url>https://aclanthology.org/2020.repl4nlp-1.7</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>45</start>
<end>54</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Bilingual Lexicon Induction with Unsupervised Post-Processing of Monolingual Word Vector Spaces
%A Vulić, Ivan
%A Korhonen, Anna
%A Glavaš, Goran
%Y Gella, Spandana
%Y Welbl, Johannes
%Y Rei, Marek
%Y Petroni, Fabio
%Y Lewis, Patrick
%Y Strubell, Emma
%Y Seo, Minjoon
%Y Hajishirzi, Hannaneh
%S Proceedings of the 5th Workshop on Representation Learning for NLP
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F vulic-etal-2020-improving
%X Work on projection-based induction of cross-lingual word embedding spaces (CLWEs) predominantly focuses on the improvement of the projection (i.e., mapping) mechanisms. In this work, in contrast, we show that a simple method for post-processing monolingual embedding spaces facilitates learning of the cross-lingual alignment and, in turn, substantially improves bilingual lexicon induction (BLI). The post-processing method we examine is grounded in the generalisation of first- and second-order monolingual similarities to the nth-order similarity. By post-processing monolingual spaces before the cross-lingual alignment, the method can be coupled with any projection-based method for inducing CLWE spaces. We demonstrate the effectiveness of this simple monolingual post-processing across a set of 15 typologically diverse languages (i.e., 15*14 BLI setups), and in combination with two different projection methods.
%R 10.18653/v1/2020.repl4nlp-1.7
%U https://aclanthology.org/2020.repl4nlp-1.7
%U https://doi.org/10.18653/v1/2020.repl4nlp-1.7
%P 45-54
Markdown (Informal)
[Improving Bilingual Lexicon Induction with Unsupervised Post-Processing of Monolingual Word Vector Spaces](https://aclanthology.org/2020.repl4nlp-1.7) (Vulić et al., RepL4NLP 2020)
ACL