Difference between revisions of "User:Eiddy"
Jump to navigation
Jump to search
m (Creating user page for new user.) |
(No difference)
|
Latest revision as of 20:57, 2 July 2017
My research interests centre on applying deep learning, reinforcement learning and Bayesian approaches to dialogue management, reward estimation and NLP tasks, with the aim of building systems that can learn directly from human interaction. I published my first ACL paper as the first author in 2016 and was awarded the best student paper award.