
	[ CLSP Homepage : Search Website ] [ Workshop 2000 Homepage ]	Tuesday, May 13, 2008

Context-sensitivity and stochastic unification-based grammars

Mark Johnson, February 29th, 2000

The first part of this talk explains why non-local context-sensitive interactions cause standard techniques for learning probabilistic grammars to be inconsistent, and motivates the more general log-linear (aka MaxEnt) models used here. The second part of the talk introduces pseudo-likelihood, and describes experiments learning stochastic unification-based grammars from corpora. The third part of the talk discusses implications of this work and the relationship between these models and optimality theory.

Seminar Schedule

The Center for Language and Speech Processing
The Johns Hopkins University
3400 North Charles Street, Barton Hall
Baltimore, MD 21218

Telephone: (410) 516-4237 Fax: (410) 516-5050 E-mail: clsp@clsp.jhu.edu

The Center for Language and Speech Processing The Johns Hopkins University 3400 North Charles Street, Barton Hall Baltimore, MD 21218
	Telephone: (410) 516-4237		Fax: (410) 516-5050		E-mail: clsp@clsp.jhu.edu