@inproceedings{hoshino-etal-2024-cross-lingual,
title = "Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity",
author = "Hoshino, Sho and
Kato, Akihiko and
Murakami, Soichiro and
Zhang, Peinan",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.371",
pages = "4164--4173",
abstract = "Learning better sentence embeddings leads to improved performance for natural language understanding tasks including semantic textual similarity (STS) and natural language inference (NLI). As prior studies leverage large-scale labeled NLI datasets for fine-tuning masked language models to yield sentence embeddings, task performance for languages other than English is often left behind. In this study, we directly compared two data augmentation techniques as potential solutions for monolingual STS: - (a): {\_}cross-lingual transfer{\_} that exploits English resources alone as training data to yield non-English sentence embeddings as zero-shot inference, and - (b) {\_}machine translation{\_} that coverts English data into pseudo non-English training data in advance. In our experiments on monolingual STS in Japanese and Korean, we find that the two data techniques yield performance on par. In addition, we find a superiority of Wikipedia domain over NLI domain as unlabeled training data for these languages. Combining our findings, we further demonstrate that the cross-lingual transfer of Wikipedia data exhibits improved performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoshino-etal-2024-cross-lingual">
<titleInfo>
<title>Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sho</namePart>
<namePart type="family">Hoshino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akihiko</namePart>
<namePart type="family">Kato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soichiro</namePart>
<namePart type="family">Murakami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peinan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Learning better sentence embeddings leads to improved performance for natural language understanding tasks including semantic textual similarity (STS) and natural language inference (NLI). As prior studies leverage large-scale labeled NLI datasets for fine-tuning masked language models to yield sentence embeddings, task performance for languages other than English is often left behind. In this study, we directly compared two data augmentation techniques as potential solutions for monolingual STS: - (a): _cross-lingual transfer_ that exploits English resources alone as training data to yield non-English sentence embeddings as zero-shot inference, and - (b) _machine translation_ that coverts English data into pseudo non-English training data in advance. In our experiments on monolingual STS in Japanese and Korean, we find that the two data techniques yield performance on par. In addition, we find a superiority of Wikipedia domain over NLI domain as unlabeled training data for these languages. Combining our findings, we further demonstrate that the cross-lingual transfer of Wikipedia data exhibits improved performance.</abstract>
<identifier type="citekey">hoshino-etal-2024-cross-lingual</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.371</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>4164</start>
<end>4173</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity
%A Hoshino, Sho
%A Kato, Akihiko
%A Murakami, Soichiro
%A Zhang, Peinan
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F hoshino-etal-2024-cross-lingual
%X Learning better sentence embeddings leads to improved performance for natural language understanding tasks including semantic textual similarity (STS) and natural language inference (NLI). As prior studies leverage large-scale labeled NLI datasets for fine-tuning masked language models to yield sentence embeddings, task performance for languages other than English is often left behind. In this study, we directly compared two data augmentation techniques as potential solutions for monolingual STS: - (a): _cross-lingual transfer_ that exploits English resources alone as training data to yield non-English sentence embeddings as zero-shot inference, and - (b) _machine translation_ that coverts English data into pseudo non-English training data in advance. In our experiments on monolingual STS in Japanese and Korean, we find that the two data techniques yield performance on par. In addition, we find a superiority of Wikipedia domain over NLI domain as unlabeled training data for these languages. Combining our findings, we further demonstrate that the cross-lingual transfer of Wikipedia data exhibits improved performance.
%U https://aclanthology.org/2024.lrec-main.371
%P 4164-4173
Markdown (Informal)
[Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity](https://aclanthology.org/2024.lrec-main.371) (Hoshino et al., LREC-COLING 2024)
ACL