32 citations · 51 across the 9 of their papers we have counts for
5 papers · 1 filter
Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan
Jordi Armengol-Estapé, Casimiro Pio Carrino, Carlos Rodriguez-Penagos +5
Multilingual language models have been a crucial breakthrough as they considerably reduce the need of data for under-resourced languages. Nevertheless, the superiority of language-…
MarIA: Spanish Language Models
Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé, Marc Pàmies +7
This work presents MarIA, a family of Spanish language models and associated resources made available to the industry and the research community. Currently, MarIA includes RoBERTa-…
Persistent Homology Captures the Generalization of Neural Networks Without A Validation Set
Asier Gutiérrez-Fandiño, David Pérez-Fernández, Jordi Armengol-Estapé +1
The training of neural networks is usually monitored with a validation (holdout) set to estimate the generalization of the model. This is done instead of measuring intrinsic proper…
Spanish Biomedical and Clinical Language Embeddings
Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé, Casimiro Pio Carrino +3
We computed both Word and Sub-word Embeddings using FastText. For Sub-word embeddings we selected Byte Pair Encoding (BPE) algorithm to represent the sub-words. We evaluated the Bi…
Characterizing and Measuring the Similarity of Neural Networks with Persistent Homology
David Pérez-Fernández, Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé +1
Characterizing the structural properties of neural networks is crucial yet poorly understood, and there are no well-established similarity measures between networks. In this work,…