esgg commited on
Commit
f71da52
1 Parent(s): 01e1121

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -4
README.md CHANGED
@@ -1,10 +1,17 @@
1
  ---
2
  license: cc-by-4.0
 
 
 
 
 
 
 
 
 
 
3
  ---
4
 
5
- ---
6
- license: cc-by-4.0
7
- ---
8
  #Software Benchmark SCIBERT model.
9
  This model is a fine-tuned version of the [SCIBERT](https://huggingface.co/allenai/scibert_scivocab_uncased) model on a dataset built based on the corpora SoMESCi and Softcite.
10
 
@@ -29,7 +36,8 @@ The corpus have been splitted in a 70-30 proportion for training and testing.
29
 
30
  The training code can be found on [Github](https://github.com/oeg-upm/software_mentions_benchmark).
31
 
32
- The results are:
 
33
  * Precision: 0.8928176795580111
34
  * Recall: 0.8568398727465536
35
  * F1-score: 0.8744588744588745
 
1
  ---
2
  license: cc-by-4.0
3
+ datasets:
4
+ - oeg/software_benchmark_v2
5
+ language:
6
+ - es
7
+ metrics:
8
+ - accuracy
9
+ library_name: transformers
10
+ tags:
11
+ - software_mentions
12
+ - scibert
13
  ---
14
 
 
 
 
15
  #Software Benchmark SCIBERT model.
16
  This model is a fine-tuned version of the [SCIBERT](https://huggingface.co/allenai/scibert_scivocab_uncased) model on a dataset built based on the corpora SoMESCi and Softcite.
17
 
 
36
 
37
  The training code can be found on [Github](https://github.com/oeg-upm/software_mentions_benchmark).
38
 
39
+ ## Evaluation Results
40
+
41
  * Precision: 0.8928176795580111
42
  * Recall: 0.8568398727465536
43
  * F1-score: 0.8744588744588745