As sophisticated as retrieval-based chatbots(Retrieval-based chatbots are used in closed-domain scenarios and rely on a collection of predefined responses to a user message. A retrieval-based bot completes three main tasks: intent classification, entity recognition, and response selection.) can get, information retrieval cannot generalize conversation (even with lots and lots of data) or generate anything new. If we want any creativity with the language used in our program’s responses as would be necessary with an open-domain system where any topic is possible we need to turn to models that facilitate new language patterns. This is where generative models shine.

By using neural networks with many hidden layers known as deep learning, generative chatbot models can build sentences that are completely original rather than retrieved from a list of possible responses.

#computer-science #chatbots #artificial-intelligence #machine-learning #deep-learning

Why use deep learning for chatbots?
1.95 GEEK