Fuli Luo

@Utsavz @weiliu620 - The 'log grad' of the policy function is the log(p(x)). - The loss function of cross-entropy is \sum q * log(p). These two are the same because...

If you use `x` -> `x` as pseudo-parallel data to pre-train the model, the model will learn a **copy** mode. Thus I recommend that you use the original sentence with...

Note: The noised sentence `x'` (lower quality) should be the **input**, not the output(ground truth), which is validated to be important by our experiments. What you need to actually do...

I reopen this issue in case someone with the same problem as you.

Do you mean why use `x'`-> `x` as pseudo-parallel corpora can achieve better results than `x`-> `x'`? @antdlx The reason is that `x'` is a style transferred sentence of `x`...

You can change `0.25` to a larger value, which can cause a better sentiment accuracy and worse content presentation. https://github.com/luofuli/DualRL/blob/2fae5bb41e62a2c1c8bd2d439baba01c9d8e4f21/dual_training.py#L275 Note: The printed logs just show the results **on one...

See [issues/17](https://github.com/luofuli/DualRL/issues/17 ).

This is a BIG question. There are many reasons that can result in training collapse. Can you provide more details? Such as the dataset, the pseudo-parallel data, the command you...

I don't know why you get this error. And I am not 100% sure that this script works. Maybe you can provide more information about this error. There is an...

The templates used to generate pseudo-parallel data are some heuristic rules. For example, the templates (or rules) for informal-to-formal text transfer includes: - Capitalize the first word and proper nouns....