Verena Rieser (Heriot-Watt University), and member of the DATAIA Institute's Scientific Advisory Board, is leading the DATAIA seminar of March 6th, on: « How machines learn to talk. Challenges and opportunities of neural approaches for Conversational AI ».

The seminar will be held remotely.

Amazon Alexa, Apple's Siri or Google's assistant are able to converse with humans using language. 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, I will review current developments including my work on using reinforcement learning and deep learning models, and evaluate these methods in the light of results from real-world applications. In particular, I will report our experience from experimenting with these models for generating responses in open-domain social dialogue as part of the Amazon Alexa Prize challenge, as well as for task-based system as part of the E2E NLG challenge - a shared task organised by my team.