Narrativa commited on
Commit
6d5f187
1 Parent(s): 4758a67

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -1
README.md CHANGED
@@ -17,7 +17,7 @@ datasets:
17
 
18
  [MLSUM es](https://huggingface.co/datasets/viewer/?dataset=mlsum)
19
 
20
- ## Results (WIP)
21
 
22
  |Set|Metric| Value|
23
  |----|------|------|
@@ -27,6 +27,20 @@ datasets:
27
  | Test | Rouge1 - fmeasure | 28.83 |
28
  | Test | RougeL - fmeasure | 23.15 |
29
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  ## Usage
31
 
32
  ```python
17
 
18
  [MLSUM es](https://huggingface.co/datasets/viewer/?dataset=mlsum)
19
 
20
+ ## Results
21
 
22
  |Set|Metric| Value|
23
  |----|------|------|
27
  | Test | Rouge1 - fmeasure | 28.83 |
28
  | Test | RougeL - fmeasure | 23.15 |
29
 
30
+ Raw metrics using HF/metrics `rouge`:
31
+
32
+ ```python
33
+ rouge = datasets.load_metric("rouge")
34
+ rouge.compute(predictions=results["pred_summary"], references=results["summary"])
35
+
36
+ {'rouge1': AggregateScore(low=Score(precision=0.30393366820245, recall=0.27905239591639935, fmeasure=0.283148902808752), mid=Score(precision=0.3068521142101569, recall=0.2817252494122592, fmeasure=0.28560373425206464), high=Score(precision=0.30972608774202665, recall=0.28458152325781716, fmeasure=0.2883786700591887)),
37
+ 'rougeL': AggregateScore(low=Score(precision=0.24184668819794716, recall=0.22401171380621518, fmeasure=0.22624104698839514), mid=Score(precision=0.24470388406868163, recall=0.22665793214539162, fmeasure=0.2289118878817394), high=Score(precision=0.2476594458951327, recall=0.22932683203591905, fmeasure=0.23153001570662513))}
38
+
39
+ rouge.compute(predictions=results["pred_summary"], references=results["summary"], rouge_types=["rouge2"])["rouge2"].mid
40
+
41
+ Score(precision=0.11423200347113865, recall=0.10588038944902506, fmeasure=0.1069921217219595)
42
+ ```
43
+
44
  ## Usage
45
 
46
  ```python