almost change the code from wildml, the code implements the Dual LSTM Encoder model from The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems.
The code here simply implements the Personalizing Dialogue Agents: I have a dog, do you have pets too?
Use the first persona sentence as input
Python 3
tensorflow 1.3
from ParlAI github
python udc_train.py
python udc_test.py --model_dir=...
python udc_predict.py --model_dir=...