Reza Qorib

> Thanks for the PR. Can you provide the links to the data (direct download or homepage), and not the paper please? Links to the paper can be added in...

@KostyaMoonlight Why do you think that way? I don't see any difference between the code at the top and the bottom, other than the bottom one ensure that there's at...

The instruction was made for the base model, you can try the t2t model for good result

I also face this issue. My F0.5 score on the BEA-2019 Test set is **72.26** while the score on CoNLL-2014 is **65.07**. However, I don't think that tokenization is the...

Hi @ZHANG45, would you mind sharing the training script and setup of your huggingface reproduction? Even better if you can also share the trained weight. I was able to reproduce...

Hi @ZHANG45 , fairseq is fine too. Would you mind sharing your code? It would be very helpful to me.

Run `git lfs pull` before the `./run.sh`