Update README.md
Browse files
README.md
CHANGED
|
@@ -23,14 +23,13 @@ Trained on 3 epochs.
|
|
| 23 |
Made by [Scoris](https://scoris.lt) team
|
| 24 |
|
| 25 |
# Evaluation:
|
| 26 |
-
Tested on scoris/en-lt-merged-data validation set.
|
| 27 |
-
|
| 28 |
| LT-EN| BLEU |
|
| 29 |
|-|------|
|
| 30 |
| scoris/scoris-mt-lt-en| 43.8 |
|
| 31 |
| Helsinki-NLP/opus-mt-tc-big-en-lt| 36.8 |
|
| 32 |
| Google Translate| 31.9 |
|
| 33 |
| Deepl| 36.1 |
|
|
|
|
| 34 |
_Google and Deepl evaluated using a random sample of 1000 sentence pairs._
|
| 35 |
|
| 36 |
According to [Google](https://cloud.google.com/translate/automl/docs/evaluate) BLEU score interpretation is following:
|
|
|
|
| 23 |
Made by [Scoris](https://scoris.lt) team
|
| 24 |
|
| 25 |
# Evaluation:
|
|
|
|
|
|
|
| 26 |
| LT-EN| BLEU |
|
| 27 |
|-|------|
|
| 28 |
| scoris/scoris-mt-lt-en| 43.8 |
|
| 29 |
| Helsinki-NLP/opus-mt-tc-big-en-lt| 36.8 |
|
| 30 |
| Google Translate| 31.9 |
|
| 31 |
| Deepl| 36.1 |
|
| 32 |
+
_Evaluated on scoris/en-lt-merged-data validation set._
|
| 33 |
_Google and Deepl evaluated using a random sample of 1000 sentence pairs._
|
| 34 |
|
| 35 |
According to [Google](https://cloud.google.com/translate/automl/docs/evaluate) BLEU score interpretation is following:
|