Endowing computers with the ability to conduct natural conversation has been a core problem of AI ever since Turing postulated what was latter dubbed ‘the Turing Test’ in the 1950s. Since then two research paths have emerged. The aim of the first approach is to model chit-chat, conversations with no particular purpose. The aim of the second approach is to model task-oriented dialogues, conversations geared towards a particular goal. An elegant framework for this gaol-oriented approach is to view a dialogue as a sequential decision-making process, in which the system learns to talk to the user in such a way that the goal of the conversation is reached. In this talk, I will explain the basics of this learning mechanism, which is applicable to a wide range of interactive learning problems.
Milica Gašić is a Professor of Dialogue Systems and Machine Learning at Heinrich Heine University Düsseldorf. Prior to her current position she was a Lecturer in Spoken Dialog Systems at the Department of Engineering, University of Cambridge where she was leading the Dialogue Systems Group. She completed her PhD under the supervision of Professor Steve Young and the topic of her thesis was Statistical Dialogue Modelling. She holds an MPhil degree in Computer Speech, Text and Internet Technology from the University of Cambridge and a Diploma in Mathematics and Computer Science from the University of Belgrade. She is a member of ACL, a member of ELLIS and a senior member of IEEE.