commit files to HF hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "neuralmind/bert-large-portuguese-cased",
+  "_name_or_path": "liaad/propbank_br_srl_bert_large_portuguese_cased",
   "architectures": [
     "BertForTokenClassification"
   ],

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

srl.py

@@ -38,17 +38,7 @@ class SRLPipeline(Pipeline):
                     current_word = word_id
                     label = -100 if word_id is None else labels[word_id]
                     new_labels.append(label)
-                elif word_id is None:
-                    # Special token
-                    new_labels.append(-100)
                 else:
-                    """
-                    # Same word as previous token
-                    label = labels[word_id]
-                    # If the label is B-XXX we change it to I-XXX
-                    if label % 2 == 1:
-                        label += 1
-                    """
                     new_labels.append(-100)
 
             results.append(new_labels)
@@ -121,8 +111,10 @@ class SRLPipeline(Pipeline):
                 if label != -100:
                     true_predictions.append(self.label_names[prediction])
 
+            doc = self.nlp(self.text.strip())
+
             outputs.append({
-                "tokens": self.text.split(),
+                "tokens": [token.text for token in doc],
                 "predictions": true_predictions,
                 "verb": self.verbs[i]
             })

tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "[PAD]",