StivenLancheros commited on
Commit
f996778
1 Parent(s): 035bbfb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -4
README.md CHANGED
@@ -8,16 +8,16 @@ metrics:
8
  - f1
9
  - accuracy
10
  model-index:
11
- - name: roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_Augmented_ES-finetuned-ner-CRAFT_Augmented_ES
12
  results: []
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
- # roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_Augmented_ES-finetuned-ner-CRAFT_Augmented_ES
19
 
20
- This model is a fine-tuned version of [StivenLancheros/roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_Augmented_ES](https://huggingface.co/StivenLancheros/roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_Augmented_ES) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
  - Loss: 0.2043
23
  - Precision: 0.8666
@@ -27,7 +27,13 @@ It achieves the following results on the evaluation set:
27
 
28
  ## Model description
29
 
30
- More information needed
 
 
 
 
 
 
31
 
32
  ## Intended uses & limitations
33
 
 
8
  - f1
9
  - accuracy
10
  model-index:
11
+ - name: roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_AugmentedTransfer_ES
12
  results: []
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
+ # roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_AugmentedTransfer_ES
19
 
20
+ This model is a fine-tuned version of [StivenLancheros/roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_Augmented_ES](https://huggingface.co/StivenLancheros/roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_Augmented_ES) on the CRAFT dataset.
21
  It achieves the following results on the evaluation set:
22
  - Loss: 0.2043
23
  - Precision: 0.8666
 
27
 
28
  ## Model description
29
 
30
+ This model performs Named Entity Recognition for 6 entity tags: Sequence, Cell, Protein, Gene, Taxon, and Chemical from the CRAFT(Colorado Richly Annotated Full Text) Corpus in Spanish (MT translated) and English. Entity tags have been normalized and replaced from the original three letter code to a full name e.g. B-Protein, I-Chemical.
31
+
32
+ This model is trained on augmented data created using Entity Replacement. 20% of the entities were replaced using a list of entities for each entity tag obtained from the official ontologies for each entity class. Three datasets (original, augmented, MT translated CRAFT) were concatenated. To improve F1 score the transfer learning was completed in two steps.
33
+
34
+ Using [StivenLancheros/roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_Augmented_ES](https://huggingface.co/StivenLancheros/roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_Augmented_ES) as a base model, I finetuned once more on the original CRAFT dataset in English.
35
+
36
+ Biobert --> Augmented CRAFT --> CRAFT ES (MT translated)
37
 
38
  ## Intended uses & limitations
39