RicardoRei
commited on
Commit
•
446dac9
1
Parent(s):
991d16d
Update README.md
Browse files
README.md
CHANGED
@@ -168,7 +168,10 @@ print (model_output.metadata.unified_scores)
|
|
168 |
|
169 |
Our model is intented to be used for **MT evaluation**.
|
170 |
|
171 |
-
Given a a triplet with (source sentence, translation, reference translation) outputs
|
|
|
|
|
|
|
172 |
|
173 |
# Languages Covered:
|
174 |
|
|
|
168 |
|
169 |
Our model is intented to be used for **MT evaluation**.
|
170 |
|
171 |
+
Given a a triplet with (source sentence, translation, reference translation) outputs three scores that reflect the translation quality according to different inputs:
|
172 |
+
- source score: [`mt`, `src`]
|
173 |
+
- reference score: [`mt`, `ref`]
|
174 |
+
- unified score: [`mt`, `src`, `ref`]
|
175 |
|
176 |
# Languages Covered:
|
177 |
|