Immaterial mail

chris@cs.[thiscity].edu

Corporeal mail

Dept. of Computer Science
University of Toronto
10 King's College Road
Rm. 3302
Toronto, ON
M5S 3G4

Office

Pratt Building, Rm. 263A
6 King's College Road
Toronto, ON

The Basics

I am a PhD candidate in computational linguistics, part of Computer Science at the University of Toronto. My advisor is Suzanne Stevenson.

I'm interested in models of child language acquisition. Learning what words mean and how to use them goes far beyond the level of learning that "apple" refers to a certain kind of tasty, crunchy orb. The lexicon of any language is full of abstract structure, and it's that structure that makes languages so productive. Suppose I said to you, "This new computer is a pain. It took me an hour and a half to glummox a paper to my advisor." Sure, I just made up the word glummox, but you can tell it has something to do with sending things. You used the structure in the verb's arguments as a cue to its meaning.

How much of that structure can we discover from the way people naturally speak? I use probabilistic topic models to show that we can learn many aspects of verb argument structure, alternation patterns and verb classes from the statistical patterns in the language children would naturally hear. At the same time, this work shows how to use messy, sparse corpus data to automatically build a detailed verb lexicon.

My MSc was also here at U of T, where I developed a Bayesian model for discovering syntactic categories from speech.

Before that, I was a member of the Centre for Theoretical Neuroscience at the University of Waterloo, where I worked on models of biologically plausible neural inhibition.



Publications and Unpublications

C. Parisien and S. Stevenson (2011). "Generalizing between form and meaning using learned verb classes." To appear in Proceedings of the 33rd Annual Conference of the Cognitive Science Society, Boston, Massachusetts, July 2011.

C. Parisien and S. Stevenson (2010). "Learning verb alternations in a usage-based Bayesian model." In Proceedings of the 32nd Annual Conference of the Cognitive Science Society, Portland, Oregon, August 2010 (pdf).

C. Parisien and S. Stevenson (2009). "Modelling the acquisition of verb polysemy in children." In Proceedings of the CogSci2009 workshop on Distributional Semantics beyond Concrete Concepts, Amsterdam, July 2009 (pdf).

C. Parisien, A. Fazly, and S. Stevenson (2008). "An incremental Bayesian model for learning syntactic categories." In Proceedings of the 12th Conference on Computational Natural Language Learning, Manchester, UK, August 2008 (pdf).

C. Parisien and P. Thagard (2008). "Robosemantics: How Stanley the Volkswagen represents the world." Minds and Machines 18(2): 169-178 (pdf).

C. Parisien, C. H. Anderson, and C. Eliasmith (2008). "Solving the problem of negative synaptic weights in cortical models." Neural Computation 20(6): 1473-1494 (pdf).

C. Parisien (2008). "An incremental Bayesian model for learning syntactic categories." Unpublished MSc thesis. Department of Computer Science, University of Toronto.

Biologically realistic neural inhibition in arbitrary neural circuits. COSYNE '06, Salt Lake City, Mar. 2006 with Chris Eliasmith and Charles H. Anderson. Poster, chosen for highlight talk.