Modelling conversation for chatbots
Modelling conversation for chatbots remains a challenge. For natural language understanding the major companies have converged on models involving intent identification and entity extraction. However, for conversation a wide range of different terminologies and models has been proposed. This talk will examine the conversation models of the main chatbot frameworks to answer questions such as: To what extent are they similar? Do current approaches go beyond hard-coded conversation flows of “happy path” dialogs 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 is an Emeritus Professor at Ulster University with a special interest in spoken language technologies. He has been researching in the field of spoken dialogue systems for more than 20 years and is the author of several books, including Spoken Dialogue Technology: Toward The Conversational User Interface (Springer, 2004), Spoken Dialogue Systems (Morgan and Claypool, 2010), with Kristiina Jokinen, and The Conversational Interface: Talking to Smart Devices (Springer, 2016), with Zoraida Callejas and David Griol.