tgamstaetter
commited on
Commit
•
9466b56
1
Parent(s):
99e9225
Update README.md
Browse files
README.md
CHANGED
@@ -12,13 +12,15 @@ model-index:
|
|
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 |
# im-bin-tf-abstr
|
19 |
|
20 |
-
This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext)
|
21 |
-
|
|
|
|
|
|
|
|
|
|
|
22 |
- Loss: 0.2750
|
23 |
- Accuracy: 0.9261
|
24 |
- F1: 0.9259
|
|
|
12 |
results: []
|
13 |
---
|
14 |
|
|
|
|
|
|
|
15 |
# im-bin-tf-abstr
|
16 |
|
17 |
+
This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext)
|
18 |
+
on a dataset of medical articles (titles only). The dataset is balanced between articles from Internal Medicine (IM) and non-IM specialties (e.g. surgery, etc.).
|
19 |
+
Class labels (non-IM = 0 vs IM = 1) are derived from the respective journal the article appeared in, i.e. if the source journal topically belonged to any subspecialty of
|
20 |
+
Internal Medicine, the class label was 1. The task was classification of titles as either 0 (non-IM) or 1 (IM).
|
21 |
+
|
22 |
+
The model achieves the following results on the evaluation set:
|
23 |
+
|
24 |
- Loss: 0.2750
|
25 |
- Accuracy: 0.9261
|
26 |
- F1: 0.9259
|