Have you ever wondered if it would be possible for computers to talk? If we could teach them to tell us what they know? Could we hire an ingenious programmer to think of all conceivable questions, come up with clever answers, and type up long lists of these? In this talk, Milica Gašić (TH 2006) will explain how researchers in machine learning approach these questions today. Please join us for the last of the THwomen40 Lecture Series.
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…
Milica Gašić (TH 2006) is the Head of Dialogue Systems Group, a Lecturer in Spoken Dialogue Systems at the Cambridge University Engineering Department and a Fellow of Murray Edwards College. She holds a BS in Computer Science and Mathematics from the University of Belgrade (2006), a MPhil in Computer Speech, Text and Internet Technology (2007) and a PhD in Engineering (2011) from the University of Cambridge. The topic of her PhD was statistical dialogue modelling and she was awarded an EPSRC PhD plus award for her dissertation. She has published more than 50 journal articles and peer reviewed conference papers and received a number of best paper awards. She is an elected member of IEEE Speech and Language Processing Technical Committee and an appointed board member of Sigdial.
Tickets will be available on the door for those who have not booked.
Members of the College are invited to use their Dining Rights to attend High Table after the lecture however please be aware that there are limited places at dinner and therefore places will be offered on a first come, first served basis. Dining Rights entitle those eligible to dine at High Table with no charge for food or wine. You can dine on any three Thursdays or Sundays in each academic year during Full Term and you may bring one guest in place of one of these occasions. Please note that anyone currently in statu pupillari and in residence at the University of Cambridge is not edible to dine at High Table. Trinity Hall students may wish to book to attend Formal Hall. We regret that we are unable to accept dining bookings for non-Trinity Hall members. High Table dining is now fully booked – if you would like your name adding to the waiting list please email firstname.lastname@example.org.
The Aula Bar will be open prior to and after the Lecture should you wish to purchase any refreshments.
Important: Please be aware that we will be filming the lecture from the back of the room. If you would prefer not to be caught on camera, please let a member of staff know when you arrive so we can seat you in an area that won’t be covered by the camera.
If you have any queries, please do not hesitate to contact the Alumni and Development Office on email@example.com or +44(0)1223 332550.
t: +44 1223 332500