@inproceedings{kajikawa-etal-2024-multi,
title = "Multi-Source Text Classification for Multilingual Sentence Encoder with Machine Translation",
author = "Kajikawa, Reon and
Yamada, Keiichiro and
Kajiwara, Tomoyuki and
Ninomiya, Takashi",
editor = "Cao, Yang (Trista) and
Papadimitriou, Isabel and
Ovalle, Anaelia and
Zampieri, Marcos and
Ferraro, Francis and
Swayamdipta, Swabha",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-srw.24",
doi = "10.18653/v1/2024.naacl-srw.24",
pages = "226--232",
abstract = "To reduce the cost of training models for each language for developers of natural language processing applications, pre-trained multilingual sentence encoders are promising.However, since training corpora for such multilingual sentence encoders contain only a small amount of text in languages other than English, they suffer from performance degradation for non-English languages.To improve the performance of pre-trained multilingual sentence encoders for non-English languages, we propose a method of machine translating a source sentence into English and then inputting it together with the source sentence in a multi-source manner.Experimental results on sentiment analysis and topic classification tasks in Japanese revealed the effectiveness of the proposed method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kajikawa-etal-2024-multi">
<titleInfo>
<title>Multi-Source Text Classification for Multilingual Sentence Encoder with Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reon</namePart>
<namePart type="family">Kajikawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keiichiro</namePart>
<namePart type="family">Yamada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoyuki</namePart>
<namePart type="family">Kajiwara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Takashi</namePart>
<namePart type="family">Ninomiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="given">(Trista)</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Papadimitriou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaelia</namePart>
<namePart type="family">Ovalle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Ferraro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To reduce the cost of training models for each language for developers of natural language processing applications, pre-trained multilingual sentence encoders are promising.However, since training corpora for such multilingual sentence encoders contain only a small amount of text in languages other than English, they suffer from performance degradation for non-English languages.To improve the performance of pre-trained multilingual sentence encoders for non-English languages, we propose a method of machine translating a source sentence into English and then inputting it together with the source sentence in a multi-source manner.Experimental results on sentiment analysis and topic classification tasks in Japanese revealed the effectiveness of the proposed method.</abstract>
<identifier type="citekey">kajikawa-etal-2024-multi</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-srw.24</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-srw.24</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>226</start>
<end>232</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Source Text Classification for Multilingual Sentence Encoder with Machine Translation
%A Kajikawa, Reon
%A Yamada, Keiichiro
%A Kajiwara, Tomoyuki
%A Ninomiya, Takashi
%Y Cao, Yang (Trista)
%Y Papadimitriou, Isabel
%Y Ovalle, Anaelia
%Y Zampieri, Marcos
%Y Ferraro, Francis
%Y Swayamdipta, Swabha
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F kajikawa-etal-2024-multi
%X To reduce the cost of training models for each language for developers of natural language processing applications, pre-trained multilingual sentence encoders are promising.However, since training corpora for such multilingual sentence encoders contain only a small amount of text in languages other than English, they suffer from performance degradation for non-English languages.To improve the performance of pre-trained multilingual sentence encoders for non-English languages, we propose a method of machine translating a source sentence into English and then inputting it together with the source sentence in a multi-source manner.Experimental results on sentiment analysis and topic classification tasks in Japanese revealed the effectiveness of the proposed method.
%R 10.18653/v1/2024.naacl-srw.24
%U https://aclanthology.org/2024.naacl-srw.24
%U https://doi.org/10.18653/v1/2024.naacl-srw.24
%P 226-232
Markdown (Informal)
[Multi-Source Text Classification for Multilingual Sentence Encoder with Machine Translation](https://aclanthology.org/2024.naacl-srw.24) (Kajikawa et al., NAACL 2024)
ACL