@inproceedings{pitarch-etal-2024-building,
title = "Building {MUSCLE}, a Dataset for {MU}ltilingual Semantic Classification of Links between Entities",
author = "Pitarch, Lucia and
Bobed Lisbona, Carlos and
Abi{\'a}n, David and
Gracia, Jorge and
Bernad, Jordi",
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.233",
pages = "2580--2594",
abstract = "In this paper we introduce MUSCLE, a dataset for MUltilingual lexico-Semantic Classification of Links between Entities. The MUSCLE dataset was designed to train and evaluate Lexical Relation Classification (LRC) systems with 27K pairs of universal concepts selected from Wikidata, a large and highly multilingual factual Knowledge Graph (KG). Each pair of concepts includes its lexical forms in 25 languages and is labeled with up to five possible lexico-semantic relations between the concepts: hypernymy, hyponymy, meronymy, holonymy, and antonymy. Inspired by Semantic Map theory, the dataset bridges lexical and conceptual semantics, is more challenging and robust than previous datasets for LRC, avoids lexical memorization, is domain-balanced across entities, and enables enrichment and hierarchical information retrieval.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pitarch-etal-2024-building">
<titleInfo>
<title>Building MUSCLE, a Dataset for MUltilingual Semantic Classification of Links between Entities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Pitarch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Bobed Lisbona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Abián</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Gracia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordi</namePart>
<namePart type="family">Bernad</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>In this paper we introduce MUSCLE, a dataset for MUltilingual lexico-Semantic Classification of Links between Entities. The MUSCLE dataset was designed to train and evaluate Lexical Relation Classification (LRC) systems with 27K pairs of universal concepts selected from Wikidata, a large and highly multilingual factual Knowledge Graph (KG). Each pair of concepts includes its lexical forms in 25 languages and is labeled with up to five possible lexico-semantic relations between the concepts: hypernymy, hyponymy, meronymy, holonymy, and antonymy. Inspired by Semantic Map theory, the dataset bridges lexical and conceptual semantics, is more challenging and robust than previous datasets for LRC, avoids lexical memorization, is domain-balanced across entities, and enables enrichment and hierarchical information retrieval.</abstract>
<identifier type="citekey">pitarch-etal-2024-building</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.233</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>2580</start>
<end>2594</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building MUSCLE, a Dataset for MUltilingual Semantic Classification of Links between Entities
%A Pitarch, Lucia
%A Bobed Lisbona, Carlos
%A Abián, David
%A Gracia, Jorge
%A Bernad, Jordi
%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 pitarch-etal-2024-building
%X In this paper we introduce MUSCLE, a dataset for MUltilingual lexico-Semantic Classification of Links between Entities. The MUSCLE dataset was designed to train and evaluate Lexical Relation Classification (LRC) systems with 27K pairs of universal concepts selected from Wikidata, a large and highly multilingual factual Knowledge Graph (KG). Each pair of concepts includes its lexical forms in 25 languages and is labeled with up to five possible lexico-semantic relations between the concepts: hypernymy, hyponymy, meronymy, holonymy, and antonymy. Inspired by Semantic Map theory, the dataset bridges lexical and conceptual semantics, is more challenging and robust than previous datasets for LRC, avoids lexical memorization, is domain-balanced across entities, and enables enrichment and hierarchical information retrieval.
%U https://aclanthology.org/2024.lrec-main.233
%P 2580-2594
Markdown (Informal)
[Building MUSCLE, a Dataset for MUltilingual Semantic Classification of Links between Entities](https://aclanthology.org/2024.lrec-main.233) (Pitarch et al., LREC-COLING 2024)
ACL