@inproceedings{sogaard-etal-2018-limitations,
title = "On the Limitations of Unsupervised Bilingual Dictionary Induction",
author = "S{\o}gaard, Anders and
Ruder, Sebastian and
Vuli{\'c}, Ivan",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-1072",
doi = "10.18653/v1/P18-1072",
pages = "778--788",
abstract = "Unsupervised machine translation - i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora - seems impossible, but nevertheless, Lample et al. (2017) recently proposed a fully unsupervised machine translation (MT) model. The model relies heavily on an adversarial, unsupervised cross-lingual word embedding technique for bilingual dictionary induction (Conneau et al., 2017), which we examine here. Our results identify the limitations of current unsupervised MT: unsupervised bilingual dictionary induction performs much worse on morphologically rich languages that are not dependent marking, when monolingual corpora from different domains or different embedding algorithms are used. We show that a simple trick, exploiting a weak supervision signal from identical words, enables more robust induction and establish a near-perfect correlation between unsupervised bilingual dictionary induction performance and a previously unexplored graph similarity metric.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sogaard-etal-2018-limitations">
<titleInfo>
<title>On the Limitations of Unsupervised Bilingual Dictionary Induction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anders</namePart>
<namePart type="family">Søgaard</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>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Unsupervised machine translation - i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora - seems impossible, but nevertheless, Lample et al. (2017) recently proposed a fully unsupervised machine translation (MT) model. The model relies heavily on an adversarial, unsupervised cross-lingual word embedding technique for bilingual dictionary induction (Conneau et al., 2017), which we examine here. Our results identify the limitations of current unsupervised MT: unsupervised bilingual dictionary induction performs much worse on morphologically rich languages that are not dependent marking, when monolingual corpora from different domains or different embedding algorithms are used. We show that a simple trick, exploiting a weak supervision signal from identical words, enables more robust induction and establish a near-perfect correlation between unsupervised bilingual dictionary induction performance and a previously unexplored graph similarity metric.</abstract>
<identifier type="citekey">sogaard-etal-2018-limitations</identifier>
<identifier type="doi">10.18653/v1/P18-1072</identifier>
<location>
<url>https://aclanthology.org/P18-1072</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>778</start>
<end>788</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Limitations of Unsupervised Bilingual Dictionary Induction
%A Søgaard, Anders
%A Ruder, Sebastian
%A Vulić, Ivan
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F sogaard-etal-2018-limitations
%X Unsupervised machine translation - i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora - seems impossible, but nevertheless, Lample et al. (2017) recently proposed a fully unsupervised machine translation (MT) model. The model relies heavily on an adversarial, unsupervised cross-lingual word embedding technique for bilingual dictionary induction (Conneau et al., 2017), which we examine here. Our results identify the limitations of current unsupervised MT: unsupervised bilingual dictionary induction performs much worse on morphologically rich languages that are not dependent marking, when monolingual corpora from different domains or different embedding algorithms are used. We show that a simple trick, exploiting a weak supervision signal from identical words, enables more robust induction and establish a near-perfect correlation between unsupervised bilingual dictionary induction performance and a previously unexplored graph similarity metric.
%R 10.18653/v1/P18-1072
%U https://aclanthology.org/P18-1072
%U https://doi.org/10.18653/v1/P18-1072
%P 778-788
Markdown (Informal)
[On the Limitations of Unsupervised Bilingual Dictionary Induction](https://aclanthology.org/P18-1072) (Søgaard et al., ACL 2018)
ACL