#217 · Primary category: AI Chatbots

seq2seq-chatbot

bot chat chatbot corpus lstm nlp python rnn tensorflow tensorlayer

Chatbot in 200 lines of code using TensorLayer

Project last updated:10/05/21

GitHub Stars

838

Forks

305

Contributors

8

License

Other

Why we included this project

This compact project is a good way to see how sequence-to-sequence models actually power a chatbot. It implements a Twitter and Cornell Movie dialogue bot in about 200 lines of Python on top of TensorLayer and TensorFlow, so you can read the whole training and inference flow without digging through a big framework. The README points to the classic seq2seq and LSTM tutorials, which helps connect the theory to runnable code. You can train it on the included corpus with one command and then chat with the model interactively, which makes it easy to see how the RNN state and decoding produce replies. If you're evaluating whether a small seq2seq baseline.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category