The major intelligent agent platforms have converged on terminology involving intent identification and entity extraction, yet use different conversational models to describe behavior. Learn how these conversational models differ and which go beyond hard-coded conversation flows of “happy path” dialogues to model conversational phenomena such as follow-up questions, changes of topic, out-of-scope utterances, and other types of edge case. What are the desiderata for intelligent conversational agents?

Michael McTear, Professor - Ulster University

Michael McTear is an Emeritus Professor at Ulster University with a special research interest in spoken language technologies. He has been researching in the field of spoken dialogue systems for more than 15 years and is the author of the widely used textbook Spoken Dialogue Technology: Toward The Conversational User Interface (Springer Verlag, 2004). He is also co-author (with Kristiina Jokinen) of the book Spoken Dialogue Systems, Morgan and Claypool, 2010, and of the book Voice Application Development for Android, Packt Publishing, 2013 (with Zoraida Callejas). A new book: The Conversational Interface: Talking to Smart Devices, co-authored with Zoraida Callejas and David Griol, was published in 2016 by Springer. Currently Michael works as a consultant for Spoken Language Technology. Michael has delivered keynote addresses at many conferences and workshops and has presented on several occasions at SpeechTEK. He is a certified VoiceXML developer and has taught VoiceXML at training courses to professionals from a range of companies. He was the main developer of the VoiceXML-based home monitoring system for patients with type-2 diabetes, currently in use at the Ulster Hospital, Northern Ireland.