Tom Kocmi
Tom Kocmi
Is it possible to compute optimization verification test? When you are translating a sentence from devset and the translation is different than reference sentence, I would like to find out...
As discussed earlier today: After continuation the tensorboard starts counting from zero. It is due to a variable seen_instances: https://github.com/ufal/neuralmonkey/blob/master/neuralmonkey/learning_utils.py#L523
I examined Nematus code: https://github.com/EdinburghNLP/nematus/blob/master/nematus/layers.py which should be the same as ours: https://github.com/ufal/neuralmonkey/blob/master/neuralmonkey/nn/ortho_gru_cell.py#L57 They use ortho_weight and norm_weight. I did not go into details if ortho_weight is equal to our...
The default output projection https://github.com/ufal/neuralmonkey/blob/master/neuralmonkey/decoders/decoder.py#L151 is tanh instead of relu, which does not reach the best score (I have experimented with this last year a bit). I would suggest to...
Following error is raised when I had a new line in config within string definition: [main] evaluation=[("target_beam", "target\n", )] ... ``` 2017-08-06 15:54:07: Failed to load INI file: Required argument...
Ve slozce s experimentem nelze pomoci git_diff souboru poznat zmeny kdyz byly na novych souborech. Neslo by napriklad jeste ukladat git status? Jenom aby bylo videt, ze existovaly nejake soubory,...
Hello, In my ongoing evaluation of metrics, I have found out, that COMET (especially source based) is very unpredictable when it evaluates a language that is not supported by XLM...
## 🚀 Feature being able to specify the batch size in terms of tokens could allow larger batch sizes. ### Motivation When training on data with various sentence lengths, increasing...