skip to content
 

Wiki, please, explain!

Wednesday 21 March: 6:00pm - 7:00pm

Mill Lane Lecture Rooms , 8 Mill Lane, CB2 1RW

Unlike most of us, computers are awfully good at quickly absorbing huge amounts of information. Unfortunately, they are less good at sharing their knowledge with us. We humans learn best through interactive conversation. And conversations are not something that comes naturally to them.

So, how we do teach computers to talk? How do we get them to tell us what they know? Perhaps, we should hire an ingenious programmer to think of all conceivable questions, come up with clever answers, and type up long lists of these? If we lower our aspirations just a little bit and aim to cater only for, say, "every conceivable question about Cambridge bus times" then such an approach is indeed possible. But your gut feeling probably (correctly) tells you that, in the long run, this is not very promising. There's no way such a rigid question-answer scheme is ever going to lead to an interactive conversation.

In this talk, Milica Gašić explains how researchers in machine learning approach this challenge today. There's been fantastic progress in recent years, as some of you may have noticed. But there's also still a long way to go …

http://mi.eng.cam.ac.uk/~mg436/

Milica Gašić is a Lecturer in Spoken Dialogue Systems at the Cambridge University Engineering Department and a Fellow of Murray Edwards College. She holds a degree in Computer Science and Mathematics from the University of Belgrade (2006), an MPhil in Computer Speech, Text and Internet Technology (2007) and a PhD in Engineering from the University of Cambridge (2011). Her PhD thesis on Statistical Dialogue Modelling won her an EPSRC PhD plus award.

Booking Information

Telephone number:
01223 766766

Booking required

Accessibility

Full access

Additional Information

Age: 12+, Talk, Arrive on time, Free

Map