Update description.md

description.md

@@ -8,6 +8,11 @@ Minimal example (evaluating English text generation)
 ```python
 import evaluate
 sescore = evaluate.load("xu1998hz/sescore")
+# for different versions of SEScore
+# sescore = evaluate.load("xu1998hz/sescore_english_mt") -> for English at Machine Translation 
+# sescore = evaluate.load("xu1998hz/sescore_german_mt") -> for German at Machine Translation
+# sescore = evaluate.load("xu1998hz/sescore_english_webnlg") -> for webnlg data-to-text
+# sescore = evaluate.load("xu1998hz/sescore_english_coco") -> for image caption
 score = sescore.compute(
     references=['sescore is a simple but effective next-generation text evaluation metric'],
     predictions=['sescore is simple effective text evaluation metric for next generation']
@@ -25,7 +30,7 @@ Currently, the following language/model pairs are available:
 |----------|-----------------|-----------------------|
 | English  | MT              | [xu1998hz/sescore_english_mt](https://huggingface.co/xu1998hz/sescore_english_mt) |
 | German   | MT              | [xu1998hz/sescore_german_mt](https://huggingface.co/xu1998hz/sescore_german_mt) |
-| English  | webNLG17        | [xu1998hz/sescore_english_webnlg17](https://huggingface.co/xu1998hz/sescore_english_webnlg17) |
+| English  | webNLG17        | [xu1998hz/sescore_english_webnlg17](https://huggingface.co/xu1998hz/sescore_english_webnlg) |
 | English  | CoCo captions   | [xu1998hz/sescore_english_coco](https://huggingface.co/xu1998hz/sescore_english_coco) |