@inproceedings{gao-etal-2024-openmsd,
title = "{O}pen{MSD}: Towards Multilingual Scientific Documents Similarity Measurement",
author = "Gao, Yang and
Ma, Ji and
Korotkov, Ivan and
Hall, Keith and
Alon, Dana and
Metzler, Donald",
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.1092",
pages = "12467--12480",
abstract = "We develop and evaluate multilingual scientific documents similarity measurement models in this work. Such models can be used to find related papers in different languages, which can help multilingual researchers find and explore papers more efficiently. We propose the first multilingual scientific documents dataset, Open-access Multilingual Scientific Documents (OpenMSD), which has 74M papers in 103 languages and 778M citation pairs. With OpenMSD, we develop multilingual SDSM models by adjusting and extending the state-of-the-art methods designed for English SDSM tasks. We find that: (i)Some highly successful methods in English SDSM yield significantly worse performance in multilingual SDSM. (ii)Our best model, which enriches the non-English papers with English summaries, outperforms strong baselines by 7{\%} (in mean average precision) on multilingual SDSM tasks, without compromising the performance on English SDSM tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2024-openmsd">
<titleInfo>
<title>OpenMSD: Towards Multilingual Scientific Documents Similarity Measurement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Korotkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keith</namePart>
<namePart type="family">Hall</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Alon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donald</namePart>
<namePart type="family">Metzler</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>We develop and evaluate multilingual scientific documents similarity measurement models in this work. Such models can be used to find related papers in different languages, which can help multilingual researchers find and explore papers more efficiently. We propose the first multilingual scientific documents dataset, Open-access Multilingual Scientific Documents (OpenMSD), which has 74M papers in 103 languages and 778M citation pairs. With OpenMSD, we develop multilingual SDSM models by adjusting and extending the state-of-the-art methods designed for English SDSM tasks. We find that: (i)Some highly successful methods in English SDSM yield significantly worse performance in multilingual SDSM. (ii)Our best model, which enriches the non-English papers with English summaries, outperforms strong baselines by 7% (in mean average precision) on multilingual SDSM tasks, without compromising the performance on English SDSM tasks.</abstract>
<identifier type="citekey">gao-etal-2024-openmsd</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1092</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>12467</start>
<end>12480</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OpenMSD: Towards Multilingual Scientific Documents Similarity Measurement
%A Gao, Yang
%A Ma, Ji
%A Korotkov, Ivan
%A Hall, Keith
%A Alon, Dana
%A Metzler, Donald
%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 gao-etal-2024-openmsd
%X We develop and evaluate multilingual scientific documents similarity measurement models in this work. Such models can be used to find related papers in different languages, which can help multilingual researchers find and explore papers more efficiently. We propose the first multilingual scientific documents dataset, Open-access Multilingual Scientific Documents (OpenMSD), which has 74M papers in 103 languages and 778M citation pairs. With OpenMSD, we develop multilingual SDSM models by adjusting and extending the state-of-the-art methods designed for English SDSM tasks. We find that: (i)Some highly successful methods in English SDSM yield significantly worse performance in multilingual SDSM. (ii)Our best model, which enriches the non-English papers with English summaries, outperforms strong baselines by 7% (in mean average precision) on multilingual SDSM tasks, without compromising the performance on English SDSM tasks.
%U https://aclanthology.org/2024.lrec-main.1092
%P 12467-12480
Markdown (Informal)
[OpenMSD: Towards Multilingual Scientific Documents Similarity Measurement](https://aclanthology.org/2024.lrec-main.1092) (Gao et al., LREC-COLING 2024)
ACL