MultiLexBATS: Multilingual Dataset of Lexical Semantic Relations
Date Issued
2024-05-22
Author(s)
Gromann, Dagmar
Gonçalo Oliveira, Hugo
Pitarch, Lucia
Apostol, Elena-Simona
Bernad, Jordi
Bytyçi, Eliot
Cantone, Chiara
Carvalho, Sara
Frontini, Francesca
Garabík, Radovan
Gracia, Jorge
Granata, Letizia
Fahad Khan, Anas
Knez, Timotej
Labropoulou, Penny
Liebeskind, Chaya
Di Buono, Maria Pia
Ostroški Anić, Ana
Rackevičienė, Sigita
Rodrigues, Ricardo
Sérasset, Gilles
Selmistraitis, Linas
Sidibé, Mahammadou
Silvano, Purificação
Spahiu, Blerina
Sogutlu, Enriketa
Stanković, Ranka
Truica, Ciprian-Octavian
Valūnaitė Oleškevičienė, Giedrė
Zitnik, Slavko
Abstract
Understanding the relation between the meanings of words is an important part of comprehending natural language. Prior work has either focused on analysing lexical semantic relations in word embeddings or probing pretrained language models (PLMs), with some exceptions. Given the rarity of highly multilingual benchmarks, it is unclear to what extent PLMs capture relational knowledge and are able to transfer it across languages. To start addressing this question, we propose MultiLexBATS, a multilingual parallel dataset of lexical semantic relations adapted from BATS in 15 languages including low-resource languages, such as Bambara, Lithuanian, and Albanian. As experiment on cross-lingual transfer of relational knowledge, we test the PLMs’ ability to (1) capture analogies across languages, and (2) predict translation targets. We find considerable differences across relation types and languages with a clear preference for hypernymy and antonymy as well as romance languages.
Subjects
File(s)![Thumbnail Image]()
Loading...
Name
2475_Paper.pdf
Size
228.37 KB
Format
Adobe PDF
Checksum
(MD5):b1ecbb671008b71b99849b3b3d4add7a