sofiaoliveira commited on
Commit
549b74c
1 Parent(s): 0a69fb4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -8
README.md CHANGED
@@ -13,7 +13,7 @@ metrics:
13
  - F1 Measure
14
  ---
15
 
16
- # MyModel
17
 
18
  ## Model description
19
 
@@ -56,15 +56,9 @@ To use the full SRL model (transformers portion + a decoding layer), refer to th
56
 
57
  - This model does not include a Tensorflow version. This is because the "type_vocab_size" in this model was changed (from 1 to 2) and, therefore, it cannot be easily converted to Tensorflow.
58
 
59
-
60
- ## Training data
61
-
62
- Pretrained weights were left identical to the original model [`xlm-roberta-base`](https://huggingface.co/xlm-roberta-base). A randomly initialized embeddings layer for "token_type_ids" was added.
63
-
64
-
65
  ## Training procedure
66
 
67
- The models were trained on the PropBank.Br datasets, using Cross-Validation. They 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](https://github.com/asofiaoliveira/srl_bert_pt).
68
 
69
  ## Eval results
70
 
 
13
  - F1 Measure
14
  ---
15
 
16
+ # XLM-R base fine-tuned on Portuguese semantic role labeling
17
 
18
  ## Model description
19
 
 
56
 
57
  - This model does not include a Tensorflow version. This is because the "type_vocab_size" in this model was changed (from 1 to 2) and, therefore, it cannot be easily converted to Tensorflow.
58
 
 
 
 
 
 
 
59
  ## Training procedure
60
 
61
+ The model was trained on the PropBank.Br datasets, 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](https://github.com/asofiaoliveira/srl_bert_pt).
62
 
63
  ## Eval results
64