PortBERT releases two RoBERTa models for Portuguese that match or beat prior monolingual and multilingual models on translated GLUE/SuperGLUE tasks while reporting training and inference times.
Lexical and orthographic distances between
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PortBERT: Navigating the Depths of Portuguese Language Models
PortBERT releases two RoBERTa models for Portuguese that match or beat prior monolingual and multilingual models on translated GLUE/SuperGLUE tasks while reporting training and inference times.