afcarl / tf_seq2seq_chatbot Goto Github PK

tensorflow seq2seq chatbot

Build a general-purpose conversational chatbot based on a hot seq2seq approach implemented in tensorflow.

The current results are pretty lousy:

hello baby	        - hello
how old are you ?   - twenty .
i am lonely	        - i am not
nice                - you ' re not going to be okay .
so rude	            - i ' m sorry .

Disclaimer:

• the answers are hand-picked (it looks cooler that way)
• chatbot has no power to follow the conversation line so far; in the example above it's a just a coincidence (hand-picked one)

Everyone is welcome to investigate the code and suggest the improvements.

Actual deeds

• realise how to diversify chatbot answers (currently the most probable one is picked and it's dull)

Papers

• Sequence to Sequence Learning with Neural Networks
• A Neural Conversational Model

Nice picture

Curtesy of this article.

Setup

git clone [email protected]:nicolas-ivanov/tf_seq2seq_chatbot.git
cd tf_seq2seq_chatbot
bash bin/setup.sh

Run

Train a seq2seq model on a small (17 MB) corpus of movie subtitles:

python bin/train.py

(this command will run the training on a CPU... GPU instructions are coming)

Test trained trained model on a set of common questions:

python bin/test.py

Chat with trained model in console:

python bin/chat.py

All configuration params are stored at tf_seq2seq_chatbot/configs/config.py

GPU usage

If you are lucky to have a proper gpu configuration for tensorflow already, this should do the job:

python bin/train.py

Otherwise you may need to build tensorflow from source and run the code as follows:

cd tensorflow  # cd to the tensorflow source folder
cp -r ~/tf_seq2seq_chatbot ./  # copy project's code to tensorflow root
bazel build -c opt --config=cuda tf_seq2seq_chatbot:train  # build with gpu-enable option
./bazel-bin/tf_seq2seq_chatbot/train  # run the built code

Requirements

• tensorflow
• tweaked version of the aforementioned Project_RNN_Enhancement lib (bash bin/setup.sh gonna get it for you)