Fostering the Ecosystem of Open Neural Encoders for Portuguese with Albertina PT* Family

Rodrigo Santos, João Rodrigues, Luís Gomes, João Ricardo Silva, António Branco, Henrique Lopes Cardoso, Tomás Freitas Osório, Bernardo Leite


Abstract
To foster the neural encoding of Portuguese, this paper contributes foundation encoder models that represent an expansion of the still very scarce ecosystem of large language models specifically developed for this language that are fully open, in the sense that they are open source and openly distributed for free under an open license for any purpose, thus including research and commercial usages. Like most languages other than English, Portuguese is low-resourced in terms of these foundational language resources, there being the inaugural 900 million parameter Albertina and 335 million Bertimbau. Taking this couple of models as an inaugural set, we present the extension of the ecosystem of state-of-the-art open encoders for Portuguese with a larger, top performance-driven model with 1.5 billion parameters, and a smaller, efficiency-driven model with 100 million parameters. While achieving this primary goal, further results that are relevant for this ecosystem were obtained as well, namely new datasets for Portuguese based on the SuperGLUE benchmark, which we also distribute openly.
Anthology ID:
2024.sigul-1.14
Volume:
Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Maite Melero, Sakriani Sakti, Claudia Soria
Venues:
SIGUL | WS
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
105–114
Language:
URL:
https://aclanthology.org/2024.sigul-1.14
DOI:
Bibkey:
Cite (ACL):
Rodrigo Santos, João Rodrigues, Luís Gomes, João Ricardo Silva, António Branco, Henrique Lopes Cardoso, Tomás Freitas Osório, and Bernardo Leite. 2024. Fostering the Ecosystem of Open Neural Encoders for Portuguese with Albertina PT* Family. In Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024, pages 105–114, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Fostering the Ecosystem of Open Neural Encoders for Portuguese with Albertina PT* Family (Santos et al., SIGUL-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.sigul-1.14.pdf