Created by: sudnya

#TODO for NMT chapter In Attention mechanism, it says Different from the simple decoder, zi is computed as:

zi+1=ϕθ‘(ci,ui,zi)

should this be zi on the left hand side and zi-1 on the right hand side of the equation?

The following under User Defined Dataset looks wonky in the html user_dataset ├── train │   ├── train_file1.src │   ├── train_file1.trg │   └── ... ├── test │   ├── test_file1.src │   ├── test_file1.trg │   └── ... ├── gen │   ├── gen_file1.src │   ├── gen_file1.trg │   └── ...

html shows: user_dataset ├── train │  ├── train_file1.src │  ├── train_file1.trg │  └── ... ├── test │  ├── test_file1.src │  ├── test_file1.trg │  └── ... ├── gen │  ├── gen_file1.src │  ├── gen_file1.trg │  └── ...

The pre-processed data also looks wonky in the html

pre-wmt14 ├── train │  └── train ├── test │  └── test ├── gen │  └── gen ├── train.list ├── test.list ├── gen.list ├── src.dict └── trg.dict

Reference 2 -> ë character in the Author's name messes up the html

Unicode in html footer looks strange: 本教程 由 PaddlePaddle 创作，采用 知识共享 署名-非商业性使用-相同方式共享 4.0 国际 许可协议进行许可。

The markdown text shows different characters eg: 知识共享许可协议 etc.