Edit model card
YAML Metadata Error: "datasets[2]" with value "Universal Dependencies" is not valid. It should not contain any whitespace. If possible, use a dataset id from the huggingface Hub.

BERTimbau large fine-tune in Portuguese Universal Dependencies and semantic role labeling

Model description

This model is the neuralmind/bert-large-portuguese-cased fine-tuned first on the Universal Dependencies Portuguese dataset and then fine-tuned on the PropBank.Br data. This is part of a project from which resulted the following models:

For more information, please see the accompanying article (See BibTeX entry and citation info below) and the project's github.

Intended uses & limitations

How to use

To use the transformers portion of this model:

from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("liaad/ud_srl-pt_bertimbau-large")
model = AutoModel.from_pretrained("liaad/ud_srl-pt_bertimbau-large")

To use the full SRL model (transformers portion + a decoding layer), refer to the project's github.

Limitations and bias

  • The model was trained only for 10 epochs in the Universal Dependencies dataset.

Training procedure

The model was trained on the Universal Dependencies Portuguese dataset; then on the CoNLL formatted OntoNotes v5.0; then on Portuguese semantic role labeling data (PropBank.Br) using 10-fold Cross-Validation. The 10 resulting models were tested on the folds as well as on a smaller opinion dataset "Buscapé". For more information, please see the accompanying article (See BibTeX entry and citation info below) and the project's github.

Eval results

Model Name F1 CV PropBank.Br (in domain) F1 Buscapé (out of domain)
srl-pt_bertimbau-base 76.30 73.33
srl-pt_bertimbau-large 77.42 74.85
srl-pt_xlmr-base 75.22 72.82
srl-pt_xlmr-large 77.59 73.84
srl-pt_mbert-base 72.76 66.89
srl-en_xlmr-base 66.59 65.24
srl-en_xlmr-large 67.60 64.94
srl-en_mbert-base 63.07 58.56
srl-enpt_xlmr-base 76.50 73.74
srl-enpt_xlmr-large 78.22 74.55
srl-enpt_mbert-base 74.88 69.19
ud_srl-pt_bertimbau-large 77.53 74.49
ud_srl-pt_xlmr-large 77.69 74.91
ud_srl-enpt_xlmr-large 77.97 75.05

BibTeX entry and citation info

      title={Transformers and Transfer Learning for Improving Portuguese Semantic Role Labeling}, 
      author={Sofia Oliveira and Daniel Loureiro and Alípio Jorge},
Downloads last month
Hosted inference API
This model can be loaded on the Inference API on-demand.