You are here

The Probabilistic Chomsky Hierarchy

Date and Time: 
Thursday, November 15, 2018. 03:00 PM - 04:15 PM
Meeting Location: 
Margaret Jacks Hall, Room 126
Workshop: 
Cognition and Language Workshop
Meeting Description: 

In keeping with the seminar theme of prediction, we consider classes of probabilistic generative models definable by machines of increasing strength (finite-state, recursive, etc.), or equivalently, by probabilistic grammars of increasing complexity, giving rise to a probabilistic version of the familiar Chomsky hierarchy. Drawing on both classic and new results, we develop some analytical tools for showing when a given probability distribution can(not) be defined at a given level of the hierarchy. Repercussions for cognitive modeling — especially in language processing and causal reasoning — are of particular interest.

Thomas Icard is assistant professor of philosophy and, by courtesy, of computer science at Stanford University.