Interdisciplinary courses in Spring 2014: Feldman, Lau & Daumé on prediction
In Spring 2014 a unique seminar, linking experts in neuroscience and computer science, will investigate how human brains and machines use context to predict upcoming sounds and words in language. Instructors Hal Daumé III (Computer Science) and Naomi Feldman and Ellen Lau (Linguistics) hope to bring together perspectives from domains that rarely intersect. Students are likely to come from diverse backgrounds: prior coursework in either cognitive neuroscience of language or in computational linguistics (or in probability/statistics or machine learning) would be a plus. Interested students are encouraged to contact one of the instructors to see if the course will be a good fit. Interested faculty, postdocs, etc. are also very welcome. Here’s the course catalog info:
Linguistic Prediction: Brains versus Machines
Hal Daumé, Naomi Feldman, & Ellen Lau
Location: MMH 1108B
Much recent work in cognitive neuroscience demonstrates that brains are engaged in predicting future input, such as upcoming words in a speech or text stream. Thirty years of research in language modeling attempts to do the same thing computationally, using models that capture various aspects of language: local configurations (n-gram models), syntactic constraints or semantic preferences. These are implemented variously as lookup-tables, parsers, recurrent neural networks, etc. This course is about understanding both sides of the prediction task: both how the brain does it, what aspects are most salient to the brain, and how this connects with computational models designed to capture various linguistic structures.