BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Situated Intelligent Interactive Systems - Zhou Yu\, CMU\, US
DTSTART:20170427T140000Z
DTEND:20170427T150000Z
UID:TALK71954@talks.cam.ac.uk
CONTACT:Anton Ragni
DESCRIPTION:Communication is an intricate dance\, an ensemble of coordinat
 ed individual actions. Imagine a future where machines interact with us li
 ke humans\, waking us up in the morning\, navigating us to work\, or discu
 ssing our daily schedules in a coordinated and natural manner. Current int
 eractive systems being developed by Apple\, Google\, Microsoft\, and Amazo
 n attempt to reach this goal by combining a large set of single-task syste
 ms. But products like Siri\, Google Now\, Cortana and Echo still follow pr
 e-specified agendas that cannot transition between tasks smoothly and trac
 k and adapt to different users naturally. My research draws on recent deve
 lopments in speech and natural language processing\, human-computer intera
 ction\, and machine learning to work towards the goal of developing *situa
 ted intelligent interactive systems*. These systems can coordinate with us
 ers to achieve effective and natural interactions. I have successfully app
 lied the proposed concepts to various tasks\, such as social conversation\
 , job interview training and movie promotion. My team's  proposal on engag
 ing social conversation systems was selected to receive $100\,000 from Ama
 zon Inc. to compete in the *Amazon Alexa Prize Challenge (*https://develop
 er.amazon.com/alexaprize).
LOCATION:Department of Engineering - James Dyson Building Seminar Room
END:VEVENT
END:VCALENDAR