Neural dialogue models: growing up confident and independent

Lecturer:

Milica Gašić (Heinrich Heine University Düsseldorf)

Neural approaches to dialogue modelling have produced state of the art results in each dialogue subtask, ranging from dialogue state tracking to user modelling. One of the biggest advantages of neural architectures for dialogue is their potential for end-to-end dialogue modelling. However, these, in many ways powerful, models have their Achilles’ heels. Their weaknesses are particularly apparent in three learning aspects, namely independence, confidence and interaction. In this talk, I will show how each of these aspects can be addressed in neural approaches to dialogue state tracking, dialogue policy estimation and user modelling.

CV:

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 the Scientific Advisory Board of DFKI, a member of ACL, a member of ELLIS and a senior member of IEEE. She currently holds an Alexander von Humboldt Sofja Kovalevskaja award and a European Research Council Starting Grant.

*** The talk will be delivered in person (MFF UK, Malostranské nám. 25, 4th floor, room S1) and will be streamed via Zoom. For details how to join the Zoom meeting, please write to sevcikova@ufal.mff.cuni.cz ***