Building a Conversational Agent Overnight with Dialogue Self-Play
Currently, AI assistants are developed and deployed in separate phases. First, designers, engineers and researchers create an agent using the latest tools and frameworks, and then the agent is deployed to chat with actual users. This approach creates inflexible agents that are restricted to skills that were encoded by the developers or inferred from the training data. In this talk, Pararth will describe an alternative approach to scale conversational agents to new tasks and enable richer conversational interactions with minimal effort on the part of the dialogue developer.
Pararth is a Machine Learning Engineer at Facebook