Bot Libre's NLP does not use deep learning, but a similar machine learning algorithm that allows the bot to analyse the words in a user's input and match it to one of its trained questions and response.
Bot Libre's NLP is a "white box" solution, not a "black box" like deep learning, so has the advantage of being configurable, and can be integrated in Bot Libre's hybrid NLP architecture that also supports patterns, state machines, and scripting. It also does not require re-training when new responses are added, and because the bot's responses are part of its "brain", it can also learn new responses in real-time and modify itself using Self.
Bot's can be configured to learn new responses from users, or live chat operators.
The Bot Libre platform also supports deep learning analytics. Bot Libre analytics can be used for any data analysis including images classification, object detection, audio recognition, NLP, and more. Bot Libre's deep learning support uses Tensorflow. Analytics are separate and not directly used by bots, but can be accessed from a bot's script through our web API.