Skip to Content.
Sympa Menu

nl-uiuc - [nl-uiuc] WEDNESDAY: AIIS talk by Prof. Suzanne Stevenson

nl-uiuc AT lists.cs.illinois.edu

Subject: Natural language research announcements

List archive

[nl-uiuc] WEDNESDAY: AIIS talk by Prof. Suzanne Stevenson


Chronological Thread 
  • From: Rajhans Samdani <rsamdan2 AT illinois.edu>
  • To: nl-uiuc AT cs.uiuc.edu, aivr AT cs.uiuc.edu, vision AT cs.uiuc.edu, eyal AT cs.uiuc.edu, aiis AT cs.uiuc.edu, aistudents AT cs.uiuc.edu, "Girju, Corina R" <girju AT illinois.edu>, "Catherine Blake" <clblake AT illinois.edu>, "Efron, Miles James" <mefron AT illinois.edu>
  • Subject: [nl-uiuc] WEDNESDAY: AIIS talk by Prof. Suzanne Stevenson
  • Date: Mon, 15 Aug 2011 11:13:10 -0500 (CDT)
  • List-archive: <http://lists.cs.uiuc.edu/pipermail/nl-uiuc>
  • List-id: Natural language research announcements <nl-uiuc.cs.uiuc.edu>

Hi all,

Prof. Suzanne Stevenson (http://www.cs.toronto.edu/~suzanne/) is giving this
week's
AIIS talk. Details below:

When: Wednesday, Aug 17, 4pm (*not* Fridat)

Where 3405 SC.

Title: Learning the meaning of words in context: A probabilistic
computational model

Abstract:
An average five-year-old knows 10,000-15,000 words, most of which she has
heard
only in ambiguous contexts – that is, when she hears an utterance, the child
must
determine which of numerous possible concepts is being talked about, and must
further figure out which word goes along with which of those meanings. The
open-
ended nature of the input to children has often been used as an argument for
the
necessity of innate, language-specific mechanisms that enable them to focus
their
learning appropriately. More recently, however, a number of researchers have
instead
claimed that general cognitive abilities should be sufficient to the task of
word
learning. We have developed a computational model that helps to shed light
on this
debate by demonstrating that word–meaning mappings can be acquired through a
general probabilistic learning mechanism. The model incrementally builds up
(probabilistic) associations between words and meanings when exposed to
naturalistic data of words in context, without the use of special biases or
constraints.
In this talk, I’ll describe the model along with some of its results on
learning low
frequency words, a particular challenge for children given the large number
of such
words and the sparsity of evidence about them.

This is joint work with Afsaneh Fazly, Afra Alishahi, Aida Nematzadeh, and
Fatemeh
Ahmadi-Fakhr.


Hoping to see you all!

Best,
Rajhans


Rajhans Samdani,
Graduate Student,
Dept. of Computer Science,
University of Illinois at Urbana-Champaign.




  • [nl-uiuc] WEDNESDAY: AIIS talk by Prof. Suzanne Stevenson, Rajhans Samdani, 08/15/2011

Archive powered by MHonArc 2.6.16.

Top of Page