Merge branch 'master' of github.com:yistLin/pytorch-dual-learning

Author: JCly-rikiu

lm/README.md

@@ -1,8 +1,10 @@
 # Language Model
 
+This language model is heavily depended on [Word-level language modeling RNN - pytorch/examples](https://github.com/pytorch/examples/tree/master/word_language_model). To train it, just use the code here and follow the steps provided there.
+
 ### Usage
 
-Reload model and dictionary first, and use `get_prob()` to get language model probability. 
+Reload pre-trained model and dictionary first, and use `get_prob()` to get language model probability. 
 
 ```python
 words = ['we', 'have', 'told', 'that', 'this', 'will']

nmt/README.md

@@ -1,8 +1,12 @@
 # Neural Machine Translation
 
-### Reference
+This NMT model is heavily depended on [pcyin/pytorch\_nmt](https://github.com/pcyin/pytorch_nmt). To train model, just follow the steps provided there.
 
-This NMT model is heavily depend on [pcyin/pytorch\_nmt](https://github.com/pcyin/pytorch_nmt).
+Basiscally, you need to:
+1. use `vocab.py` to generate vocab file
+2. use `nmt.py` to train model
+
+And you may find `scripts/train.sh` helpful.
 
 ### Test Results