Gervásio PT-* is a foundation, large language model for the Portuguese language. It is a decoder of the GPT family, based on the neural architecture Transformer and developed over the Pythia model, with competitive performance for this language. It has different versions that were trained for ...

This resource contains a pre-trained BERT language model trained on the Portuguese language. A BERT-Base cased variant was trained on the BrWaC (Brazilian Web as Corpus), a large Portuguese corpus, for 1,000,000 steps, using whole-word mask. The model is available as artifacts for TensorFlow and...

The CINTIL-WordSenses corpus, built upon the CINTIL International Corpus of Portuguese (Barreto et al., 2006), is composed of 23,825 sentences of written Portuguese with open-class terms manually disambiguated and annotated with synset identifiers from the Portuguese MultiWordNet (MWNPT) (Pianti ...

CIPM is a set of historical, religious, notarial, literary texts in prose and verse, written in medieval portuguese. It has around 3.5 million words.

CIPM-POS is a set of historical, religious, notarial, literary texts in prose and verse, written is medieval portuguese. It contains around 88000 words.

The test set described in was used as the basis for the assessment of word embeddings. An example entry in this data set would read: ‘Berlin Germany Lisbon Portugal’. With these four words relations – as in this example – one can test semantic analogies by using any of the possible combinations o...