-
According the paper for self-bleu calculations each generation is compared against all the **other** references.
The current Self-BLEU implementation includes the selected hypothesis in the list o…
-
def compute_score(self, gts, res):
assert(gts.keys() == res.keys())
imgIds = gts.keys()
bleu_scorer = BleuScorer(n=self._n)
for id in imgIds:
…
-
When I train a new model in flickr8k and flickr30k dataset in my environment, I find that the **trianing loss is too high**(about 10) and the **bleu-4 is too low**(about 2.4e-232) after 20 epochs. It …
-
Hi,
I tried to train the model with Flickr30K dataset, but when I tested, I got Bleu-4 score of 0.16137 which is away lower than the results that reported in the paper. Based in your comments in othe…
-
mhrmm updated
4 years ago
-
### Description
The report
> N sentences where **Sys A** > **Sys B** at sentence-level BLEU
will generate wrong output if:
a) Sys A never generates sentences that have a higher BLEU scor…
-
-
I found this error when running your code with tensorflow
from bleu_scorer import BleuScorer
ModuleNotFoundError: No module named 'bleu_scorer'
-
## 🐛 Bug
The training of the [Translation model](https://github.com/pytorch/fairseq/tree/master/examples/translation) fails with
```
AttributeError: module 'sacrebleu' has no attribute 'compute_…
-
On Running the example given in the code, I am receiving the following error:
Seems some issue with not able to find a java library:
```bash
Reasons: [no lmdbjni64-0.4.6 in java.library.path, no l…