diff --git a/README.md b/README.md
index 4ff3638..6838137 100644
--- a/README.md
+++ b/README.md
@@ -4,7 +4,12 @@
 * tensorflow r1.1
 
 ### References
+- [Neural Machine Translation by Jointly Learning to Align and Translate](https://arxiv.org/abs/1409.0473)
 - [Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation](https://arxiv.org/pdf/1406.1078.pdf)
 - [A Neural Conversational Model](https://arxiv.org/pdf/1506.05869.pdf)
 - [A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion](https://arxiv.org/pdf/1507.02221.pdf)
 - [Attention with Intention for a Neural Network Conversation Model](https://arxiv.org/pdf/1510.08565.pdf)
+
+### TODOs
+* anti-language model to suppress generic response
+* MMI-loss as objective function