nashid

@oathaha, after reading the paper, I see that tokens are added as part of the input. The model does not treat any token differently.

Thanks @luozhouyang. I will definitely have a look at the [nmt_with_attention](https://www.tensorflow.org/tutorials/text/nmt_with_attention) tutorial. Actually, at first I was thinking to use the model from that tutorial. However, I was not sure...

@longsamaa are you able to triage this issue?

Found the issue, some input line consisted of multiple spaces which NMT failed to handle i.e.: ``` aa. a. a. aa abc abd zcc dwawdfeef ``` Apparently, here line2 was...

Hi Vincent, this was exactly my plan. After reading the PLUR paper, my impression was one major contribution of that paper is the open-sourced framework of PLUR that others can...

@pkuzqh my email address is [email protected]. Can you please share the related code with me?

@pkuzqh do you have a tentative timeline of when the tree-sitter implementation will be available?

> Since our code processing the raw method is written based on the grammar of Java, it needs you to write a new script to process the code written in...

@pkuzqh we need the JS support for [Recoder](https://github.com/pkuzqh/Recoder) in the coming weeks. It appears we should look into the implementation of`runsolvereplace2.py` script and mimic the logic for JS. That said...

> sorry， it is in https://disk.pku.edu.cn:443/link/37FED995C8031D4DB8212BC517ECC3A1. Maybe I need several months to change the grammar used in our tools. I am trying to download `newdata.zip` from https://disk.pku.edu.cn:443/link/37FED995C8031D4DB8212BC517ECC3A1. However, its timing...