@inproceedings{wada-etal-2019-unsupervised,
title = "Unsupervised Multilingual Word Embedding with Limited Resources using Neural Language Models",
author = "Wada, Takashi and
Iwata, Tomoharu and
Matsumoto, Yuji",
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/P19-1300",
doi = "10.18653/v1/P19-1300",
pages = "3113--3124",
abstract = "Recently, a variety of unsupervised methods have been proposed that map pre-trained word embeddings of different languages into the same space without any parallel data. These methods aim to find a linear transformation based on the assumption that monolingual word embeddings are approximately isomorphic between languages. However, it has been demonstrated that this assumption holds true only on specific conditions, and with limited resources, the performance of these methods decreases drastically. To overcome this problem, we propose a new unsupervised multilingual embedding method that does not rely on such assumption and performs well under resource-poor scenarios, namely when only a small amount of monolingual data (i.e., 50k sentences) are available, or when the domains of monolingual data are different across languages. Our proposed model, which we call {`}Multilingual Neural Language Models{'}, shares some of the network parameters among multiple languages, and encodes sentences of multiple languages into the same space. The model jointly learns word embeddings of different languages in the same space, and generates multilingual embeddings without any parallel data or pre-training. Our experiments on word alignment tasks have demonstrated that, on the low-resource condition, our model substantially outperforms existing unsupervised and even supervised methods trained with 500 bilingual pairs of words. Our model also outperforms unsupervised methods given different-domain corpora across languages. Our code is publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wada-etal-2019-unsupervised">
<titleInfo>
<title>Unsupervised Multilingual Word Embedding with Limited Resources using Neural Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Takashi</namePart>
<namePart type="family">Wada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoharu</namePart>
<namePart type="family">Iwata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</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>Recently, a variety of unsupervised methods have been proposed that map pre-trained word embeddings of different languages into the same space without any parallel data. These methods aim to find a linear transformation based on the assumption that monolingual word embeddings are approximately isomorphic between languages. However, it has been demonstrated that this assumption holds true only on specific conditions, and with limited resources, the performance of these methods decreases drastically. To overcome this problem, we propose a new unsupervised multilingual embedding method that does not rely on such assumption and performs well under resource-poor scenarios, namely when only a small amount of monolingual data (i.e., 50k sentences) are available, or when the domains of monolingual data are different across languages. Our proposed model, which we call ‘Multilingual Neural Language Models’, shares some of the network parameters among multiple languages, and encodes sentences of multiple languages into the same space. The model jointly learns word embeddings of different languages in the same space, and generates multilingual embeddings without any parallel data or pre-training. Our experiments on word alignment tasks have demonstrated that, on the low-resource condition, our model substantially outperforms existing unsupervised and even supervised methods trained with 500 bilingual pairs of words. Our model also outperforms unsupervised methods given different-domain corpora across languages. Our code is publicly available.</abstract>
<identifier type="citekey">wada-etal-2019-unsupervised</identifier>
<identifier type="doi">10.18653/v1/P19-1300</identifier>
<location>
<url>https://aclanthology.org/P19-1300</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>3113</start>
<end>3124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Multilingual Word Embedding with Limited Resources using Neural Language Models
%A Wada, Takashi
%A Iwata, Tomoharu
%A Matsumoto, Yuji
%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 wada-etal-2019-unsupervised
%X Recently, a variety of unsupervised methods have been proposed that map pre-trained word embeddings of different languages into the same space without any parallel data. These methods aim to find a linear transformation based on the assumption that monolingual word embeddings are approximately isomorphic between languages. However, it has been demonstrated that this assumption holds true only on specific conditions, and with limited resources, the performance of these methods decreases drastically. To overcome this problem, we propose a new unsupervised multilingual embedding method that does not rely on such assumption and performs well under resource-poor scenarios, namely when only a small amount of monolingual data (i.e., 50k sentences) are available, or when the domains of monolingual data are different across languages. Our proposed model, which we call ‘Multilingual Neural Language Models’, shares some of the network parameters among multiple languages, and encodes sentences of multiple languages into the same space. The model jointly learns word embeddings of different languages in the same space, and generates multilingual embeddings without any parallel data or pre-training. Our experiments on word alignment tasks have demonstrated that, on the low-resource condition, our model substantially outperforms existing unsupervised and even supervised methods trained with 500 bilingual pairs of words. Our model also outperforms unsupervised methods given different-domain corpora across languages. Our code is publicly available.
%R 10.18653/v1/P19-1300
%U https://aclanthology.org/P19-1300
%U https://doi.org/10.18653/v1/P19-1300
%P 3113-3124
Markdown (Informal)
[Unsupervised Multilingual Word Embedding with Limited Resources using Neural Language Models](https://aclanthology.org/P19-1300) (Wada et al., ACL 2019)
ACL