@inproceedings{wang-etal-2018-exploiting,
title = "Exploiting Common Characters in {C}hinese and {J}apanese to Learn Cross-Lingual Word Embeddings via Matrix Factorization",
author = "Wang, Jilei and
Luo, Shiying and
Shi, Weiyan and
Dai, Tao and
Xia, Shu-Tao",
editor = "Augenstein, Isabelle and
Cao, Kris and
He, He and
Hill, Felix and
Gella, Spandana and
Kiros, Jamie and
Mei, Hongyuan and
Misra, Dipendra",
booktitle = "Proceedings of the Third Workshop on Representation Learning for {NLP}",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3015",
doi = "10.18653/v1/W18-3015",
pages = "113--121",
abstract = "Learning vector space representation of words (i.e., word embeddings) has recently attracted wide research interests, and has been extended to cross-lingual scenario. Currently most cross-lingual word embedding learning models are based on sentence alignment, which inevitably introduces much noise. In this paper, we show in Chinese and Japanese, the acquisition of semantic relation among words can benefit from the large number of common characters shared by both languages; inspired by this unique feature, we design a method named CJC targeting to generate cross-lingual context of words. We combine CJC with GloVe based on matrix factorization, and then propose an integrated model named CJ-Glo. Taking two sentence-aligned models and CJ-BOC (also exploits common characters but is based on CBOW) as baseline algorithms, we compare them with CJ-Glo on a series of NLP tasks including cross-lingual synonym, word analogy and sentence alignment. The result indicates CJ-Glo achieves the best performance among these methods, and is more stable in cross-lingual tasks; moreover, compared with CJ-BOC, CJ-Glo is less sensitive to the alteration of parameters.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2018-exploiting">
<titleInfo>
<title>Exploiting Common Characters in Chinese and Japanese to Learn Cross-Lingual Word Embeddings via Matrix Factorization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jilei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiying</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiyan</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shu-Tao</namePart>
<namePart type="family">Xia</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 Third Workshop on Representation Learning for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kris</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Hill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Jamie</namePart>
<namePart type="family">Kiros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyuan</namePart>
<namePart type="family">Mei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipendra</namePart>
<namePart type="family">Misra</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>Learning vector space representation of words (i.e., word embeddings) has recently attracted wide research interests, and has been extended to cross-lingual scenario. Currently most cross-lingual word embedding learning models are based on sentence alignment, which inevitably introduces much noise. In this paper, we show in Chinese and Japanese, the acquisition of semantic relation among words can benefit from the large number of common characters shared by both languages; inspired by this unique feature, we design a method named CJC targeting to generate cross-lingual context of words. We combine CJC with GloVe based on matrix factorization, and then propose an integrated model named CJ-Glo. Taking two sentence-aligned models and CJ-BOC (also exploits common characters but is based on CBOW) as baseline algorithms, we compare them with CJ-Glo on a series of NLP tasks including cross-lingual synonym, word analogy and sentence alignment. The result indicates CJ-Glo achieves the best performance among these methods, and is more stable in cross-lingual tasks; moreover, compared with CJ-BOC, CJ-Glo is less sensitive to the alteration of parameters.</abstract>
<identifier type="citekey">wang-etal-2018-exploiting</identifier>
<identifier type="doi">10.18653/v1/W18-3015</identifier>
<location>
<url>https://aclanthology.org/W18-3015</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>113</start>
<end>121</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting Common Characters in Chinese and Japanese to Learn Cross-Lingual Word Embeddings via Matrix Factorization
%A Wang, Jilei
%A Luo, Shiying
%A Shi, Weiyan
%A Dai, Tao
%A Xia, Shu-Tao
%Y Augenstein, Isabelle
%Y Cao, Kris
%Y He, He
%Y Hill, Felix
%Y Gella, Spandana
%Y Kiros, Jamie
%Y Mei, Hongyuan
%Y Misra, Dipendra
%S Proceedings of the Third Workshop on Representation Learning for NLP
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F wang-etal-2018-exploiting
%X Learning vector space representation of words (i.e., word embeddings) has recently attracted wide research interests, and has been extended to cross-lingual scenario. Currently most cross-lingual word embedding learning models are based on sentence alignment, which inevitably introduces much noise. In this paper, we show in Chinese and Japanese, the acquisition of semantic relation among words can benefit from the large number of common characters shared by both languages; inspired by this unique feature, we design a method named CJC targeting to generate cross-lingual context of words. We combine CJC with GloVe based on matrix factorization, and then propose an integrated model named CJ-Glo. Taking two sentence-aligned models and CJ-BOC (also exploits common characters but is based on CBOW) as baseline algorithms, we compare them with CJ-Glo on a series of NLP tasks including cross-lingual synonym, word analogy and sentence alignment. The result indicates CJ-Glo achieves the best performance among these methods, and is more stable in cross-lingual tasks; moreover, compared with CJ-BOC, CJ-Glo is less sensitive to the alteration of parameters.
%R 10.18653/v1/W18-3015
%U https://aclanthology.org/W18-3015
%U https://doi.org/10.18653/v1/W18-3015
%P 113-121
Markdown (Informal)
[Exploiting Common Characters in Chinese and Japanese to Learn Cross-Lingual Word Embeddings via Matrix Factorization](https://aclanthology.org/W18-3015) (Wang et al., RepL4NLP 2018)
ACL