| language: | |
| - pt | |
| - gl | |
| - multilingual | |
| license: gpl-3.0 | |
| widget: | |
| - text: A minha amiga Rosa, de S�o Paulo, estudou en Montreal. Agora trabalha em Santiago | |
| de Compostela com o M�rio. | |
| # Named Entity Recognition (NER) model for Portuguese | |
| This is a NER model for Portuguese which uses the standard 'enamex' classes: LOC (geographical locations); PER (people); ORG (organizations); MISC (other entities). | |
| The model is based on [BERTimbau Base](https://huggingface.co/neuralmind/bert-base-portuguese-cased), which has been fine-tuned using a combination of available corpora (see [1] for details). | |
| There is an alternative model trained using [BERTimbau Large](https://huggingface.co/neuralmind/bert-large-portuguese-cased): [bert-large-pt-ner-enamex](https://huggingface.co/marcosgg/bert-large-pt-ner-enamex). | |
| It was trained with a batch size of 8 and a learning rate of 2e-5 during 3 epochs. It achieved the following results on the test set (Precision/Recall/F1): 0.913/0.918/0.915. | |
| [1] Pablo Gamallo, Marcos Garcia & Patricia Mart�n-Rodilla, 2019. [NER and open information extraction for Portuguese notebook for IberLEF 2019 Portuguese named entity recognition and relation extraction tasks](https://ceur-ws.org/Vol-2421/NER_Portuguese_paper_6.pdf). In _Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2019) | |
| co-located with 35th Conference of the Spanish Society for Natural Language Processing (SEPLN 2019)_: 457-467. |