Update README.md
Browse files
README.md
CHANGED
|
@@ -51,14 +51,11 @@ Huggingface Datasets library.
|
|
| 51 |
```
|
| 52 |
"rouge{n}" (e.g. `"rouge1"`, `"rouge2"`) where: {n} is the n-gram based scoring,
|
| 53 |
"rougeL": Longest common subsequence based scoring.
|
| 54 |
-
"rougeLSum": rougeLsum splits text using "
|
| 55 |
-
"
|
| 56 |
```
|
| 57 |
|
| 58 |
-
* Rouge1:
|
| 59 |
-
* Rouge2: 9
|
| 60 |
-
* RougeL:
|
| 61 |
-
* rougeLsum: 24.2696
|
| 62 |
|
| 63 |
-
These scores are expected to improve
|
| 64 |
for the CNN DM and XSUM datasets (translated to Dutch) individually.
|
|
|
|
| 51 |
```
|
| 52 |
"rouge{n}" (e.g. `"rouge1"`, `"rouge2"`) where: {n} is the n-gram based scoring,
|
| 53 |
"rougeL": Longest common subsequence based scoring.
|
|
|
|
|
|
|
| 54 |
```
|
| 55 |
|
| 56 |
+
* Rouge1: 23.8
|
| 57 |
+
* Rouge2: 6.9
|
| 58 |
+
* RougeL: 19.7
|
|
|
|
| 59 |
|
| 60 |
+
These scores are expected to improve if the model is trained with evaluation configured
|
| 61 |
for the CNN DM and XSUM datasets (translated to Dutch) individually.
|