Update README.md
Browse files
README.md
CHANGED
@@ -34,7 +34,7 @@ The model is evaluated on 400 validation sentences.
|
|
34 |
- Validation loss: 1.56
|
35 |
- BLEU: 0.13
|
36 |
|
37 |
-
_Note: Since the Axolotl corpus contains multiple misalignments, the real BLEU and Validation loss are slightly better.
|
38 |
|
39 |
|
40 |
## References
|
|
|
34 |
- Validation loss: 1.56
|
35 |
- BLEU: 0.13
|
36 |
|
37 |
+
_Note: Since the Axolotl corpus contains multiple misalignments, the real BLEU and Validation loss are slightly better. These misalignments also introduce noise into the training._
|
38 |
|
39 |
|
40 |
## References
|