impresso-project
/

ner-stacked-bert-multilingual

Token Classification

Model card Files Files and versions Community

emanuelaboros commited on Aug 9, 2024

Commit

08dfe16

·

verified ·

1 Parent(s): b7624fb

Update generic_ner.py

Files changed (1) hide show

generic_ner.py +9 -2

generic_ner.py CHANGED Viewed

@@ -87,10 +87,17 @@ def get_entities(tokens, tags, confidences, text):
             for indices in find_entity_indices(text, original_string):
                 entity_start_position = indices[0]
                 entity_end_position = indices[1]
-                if '_'.join([original_label, original_string, entity_start_position]) in already_done:
                     continue
                 else:
-                    already_done.append('_'.join([original_label, original_string, entity_start_position]))
                 entities.append(
                     {
                         "entity": original_label,

             for indices in find_entity_indices(text, original_string):
                 entity_start_position = indices[0]
                 entity_end_position = indices[1]
+                if (
+                    "_".join([original_label, original_string, str(entity_start_position)])
+                    in already_done
+                ):
                     continue
                 else:
+                    already_done.append(
+                        "_".join(
+                            [original_label, original_string, str(entity_start_position)]
+                        )
+                    )
                 entities.append(
                     {
                         "entity": original_label,