MultiLexBATS: Multilingual Dataset of Lexical Semantic Relations - GETALP Access content directly
Conference Papers Year : 2024

MultiLexBATS: Multilingual Dataset of Lexical Semantic Relations

Timotej Knez
  • Function : Author
  • PersonId : 1373349
Sigita Rackevičienė
  • Function : Author
  • PersonId : 1373353
Ricardo Rodrigues
  • Function : Author
  • PersonId : 1373354
Linas Selmistraitis
  • Function : Author
  • PersonId : 1373355
Enriketa Sogutlu
  • Function : Author
  • PersonId : 1373358
Slavko Zitnik
  • Function : Author
  • PersonId : 1005361


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.
Fichier principal
Vignette du fichier
2475_Paper.pdf (228.37 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04539892 , version 1 (09-04-2024)


  • HAL Id : hal-04539892 , version 1


Dagmar Gromann, Hugo Gonçalo Oliveira, Lucia Pitarch, Elena-Simona Apostol, Jordi Bernad, et al.. MultiLexBATS: Multilingual Dataset of Lexical Semantic Relations. Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), ELDA; ICCL, May 2024, Torino, Italy. pp.11783--11793. ⟨hal-04539892⟩
30 View
162 Download


Gmail Mastodon Facebook X LinkedIn More