Xiong Ma

Results 15 issues of Xiong Ma

@santhoshkolloju when you train this model, do you use bert embedding as abstract embedding, it mean article and abstract will go through bert when train this summary model?

[transformer-generator](https://github.com/policeme/transformer-pointer-generator)

@Kyubyong ![image](https://user-images.githubusercontent.com/30991932/54262578-78346500-45a9-11e9-9d34-483b4d621b36.png)

![image](https://user-images.githubusercontent.com/30991932/56713986-f453c800-6765-11e9-9c79-284d5c979cce.png) @Kyubyong in this code, why use self.embedding, why not redefine a matrix, is there a another meaning?

@Kyubyong droupout rate in paper is 0.1, but there is 0.3, is any different between you and paper? paper: ![image](https://user-images.githubusercontent.com/30991932/57909785-4f389500-78b6-11e9-8c3f-0ea00c55c81e.png)

@Kyubyong when I run download.sh, I got this error ![image](https://user-images.githubusercontent.com/30991932/53225123-f2ac4c00-36b1-11e9-8af1-c412a0364b21.png) when I download this dataset, I didn't find be.vocab, can you tell where can be found? thx.

@Kyubyong I am very confuse at encoder's block and decoder's block, if we have one block in encoder, it means we have one encoder? if we have two blocks in...