Rasa: open source conversational AI to build next generation chatbots
summary
Rasa provides open source Python libraries that actually show how intent classification uses pretrained word vectors averaged, entity extraction uses conditional random fields, and dialogue management runs an LSTM that learns context and supports interactive online learning. The project reports 45 contributors to Rasa NLU, 4 contributors to Rasa Core, and about 20,000 developers using the tools. Demoed features include a Wikipedia-retrieval bot, domain YAML, pip install, slots, custom Python actions and on-the-fly correction with immediate retraining.
AI-written summary · about
chapters (7)
related talks
30mConversational AI: Building clever chatbots
01h 38mConversational AI with Rasa Core & NLU
01h 27mDeprecating the state machine: building conversational AI with the Rasa stack
01h 31mGoing beyond “Sorry, I didn’t get that” building AI assistants that scale...
55mDemystifying Natural Language Processing across several industry verticals
01h 29mGoing Beyond “Sorry, I Didn’t Get That”: Building AI Assistants that Scale...
34mWriting a Chatbot in PHP
33mBuilding the next-generation Conversational AI with Python and Deep Learning