Skip to Content.
Sympa Menu

nl-uiuc - [nl-uiuc] Mark Johnson talk Monday, April 7@4pm

nl-uiuc AT lists.cs.illinois.edu

Subject: Natural language research announcements

List archive

[nl-uiuc] Mark Johnson talk Monday, April 7@4pm


Chronological Thread 
  • From: Julia Hockenmaier <juliahmr AT uiuc.edu>
  • To: nl-uiuc AT cs.uiuc.edu
  • Subject: [nl-uiuc] Mark Johnson talk Monday, April 7@4pm
  • Date: Thu, 03 Apr 2008 17:01:26 -0500
  • List-archive: <http://lists.cs.uiuc.edu/pipermail/nl-uiuc>
  • List-id: Natural language research announcements <nl-uiuc.cs.uiuc.edu>


Computer Science Distinguished Lectureship Series

Bayesian models of language acquisition,
Or, Where do the rules come from?

Mark Johnson, Brown University
Monday April 7 2008, 4:00pm
1404 Siebel Center, Department of Computer Science, UIUC


Each human language contains an astronomically large (if not unbounded) number of different sentences. How can something so large and complex possibly be learned? Over the past decade and a half we've figured out how to define probability distributions over grammars and the linguistic structures they generate, opening up the possibility of Bayesian models of language acquisition. Bayesian approaches are particularly attractive because they can exploit "prior" (e.g., innate) knowledge as well as statistical generalizations from the input. Bayesian learners have two major advantages over other approaches. First, because the generalizations they learn and the prior knowledge they utilize are both expressed in terms of explicit representations, it is clear what is learned and what information is exploited during learning. Second, because of the "curse of dimensionality", learners that identify and exploit structural properties of their input seem to be the only ones that have a chance of "scaling up" to learn real languages. This talk describes Bayesian methods for learning Context-Free Grammars and a generalization of them that we call Adaptor Grammars, and applies them to problems of morphological acquisition and word segmentation.

Bio:

Mark Johnson is Professor of Cognitive and Linguistic Sciences and Computer Science at Brown University. After getting his BSc (Hons) from the University of Sydney in Australia, he obtained an MA from UCSD and a PhD from Stanford. He held a postdoctoral fellowship at MIT. He has been a visiting researcher at the University of Stuttgart, the Xerox Research Centre in Grenoble, CSAIL at MIT and Microsoft Research. He was President of the Association for Computational Linguistics in 2003.

http://www.cog.brown.edu/~mj/


Note:
We still have a few slots on Mark's schedule. If you want to meet him, please email Ronda Pellegrini (rpellegr AT cs.uiuc.edu).




  • [nl-uiuc] Mark Johnson talk Monday, April 7@4pm, Julia Hockenmaier, 04/03/2008

Archive powered by MHonArc 2.6.16.

Top of Page