Update README.md

README.md

@@ -8,16 +8,16 @@ metrics:
 - f1
 - accuracy
 model-index:
-- name: roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_Augmented_ES-finetuned-ner-CRAFT_Augmented_ES
+- name: roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_AugmentedTransfer_ES
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_Augmented_ES-finetuned-ner-CRAFT_Augmented_ES
+# roberta-base-biomedical-clinical-es-finetuned-ner-CRAFT_AugmentedTransfer_ES
 
-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.
+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.
 It achieves the following results on the evaluation set:
 - Loss: 0.2043
 - Precision: 0.8666
@@ -27,7 +27,13 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+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.
+
+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.
+
+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.
+
+Biobert --> Augmented CRAFT --> CRAFT ES (MT translated)
 
 ## Intended uses & limitations