Intelligent virtual agents frequently engage the user in conversation. The underlying technology - often referred to as spoken dialogue systems - have experienced a revolution over the past decade, moving from being completely handcrafted to using data-driven machine learning methods.
In this talk, Professor Verena Rieser will review current developments including her work on using reinforcement learning and deep learning models, and evaluate these methods in the light of recent results from two large-scale studies: First, Verena will summarise results from the End-to-End NLG Challenge for presenting information in closed-domain, task-based dialogue systems [1]. Second, she will report on experiences from experimenting with these models for generating responses in open-domain social dialogue as part of the Amazon Alexa Prize challenge [2].