[Colloquium] TTIC Talks: Shay Cohen, CMU

[Liv Leader]

When:     *Wednesday, April 6 @ 11*

Where:   * TTIC Conference Room #526*, 6045 S. Kenwood Ave, 5th Floor

Who:     *Shay Cohen*, CMU

Title:      *Probabilistic Modeling for Unsupervised Learning of Syntax*

We are facing enormous growth in the amount of information available from
various data resources. This growth is even more notable when it comes to
text data; the internet, for example, is expected to double itself
every five years, with billions of multilingual webpages available.

Computational linguistics is precisely equipped with the tools and
principles to
process such textual information. Since the 1990s, approaches to developing
various systems for text analysis have been data-driven: researchers collect
text data, annotate according to the task at hand, and then learn to
annotate
new data instances using statistical learning algorithms. Yet, such
annotation
is expensive and time consuming. A newer trend in computational linguistics
focuses on unsupervised learning: learning from data in its raw form,
without
any kind of annotation.

I will address the problem of unsupervised learning of syntax for natural
language, a problem situated in the core of computational linguistics. I
will
describe the challenges inherent in this kind of learning, and demonstrate
how we can overcome them using a Bayesian framework for statistical learning
of probabilistic grammars. I will also discuss some extensions of this
work in the nonprojective setting (a type of syntactic construct) and the
multilingual setting.

Host: Karen Livescu, klivescu at ttic.edu

-- 
Liv Leader
Faculty Services

Toyota Technological Institute
6045 S Kenwood Ave, #504
Chicago, IL 60637
Phone- (773) 834-2567
Fax-     (773) 834-9881
Email-  lleader at ttic.edu <jam at ttic.edu>
Web-   www.ttic.edu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20110330/371bedcc/attachment.htm