CSLI Calendar corrections/additions

[Emma Pease <emma@csli.Stanford.EDU>]

1. The CCRMA Hearing Seminar listed as being on Tuesday, 16 November
at 11:00am will actually be

WEDNESDAY, 17 NOVEMBER
        10:00am CCRMA Hearing Seminar
                CCRMA Library
                Bruno Repp
                http://www-ccrma.stanford.edu/CCRMA/Events/Events.html#hearing

2. The location for the following was misspelled in the Calendar.
Annenberg Auditorium is in the Cummings Art Bldg.

   As you look at the Quad, the Art Gallery is on your left, across a
   wide walkway. Cummings Art Building behind it, toward the center of
   campus. Annenberg Auditorium is in the basement. Enter by descending
   the brick staircase behind the Art Gallery.
   
   Permit parking enforcement will not take place after 4:00pm.

The Symbolic Systems Student Society presents:

               The 1999-2000 Distinguished Speaker Event
                     Thursday, November 18, 1999
                     4 PM, Annenberg Auditorium

                       a dialogue featuring:
                 Doug Engelbart, inventor of the mouse
              Steven Johnson, author of _Interface Culture_

                    "Augmenting the Human Intellect"
   How does new technology transform the way we create and communicate?
       A dialogue between one of the web's intellectual heavyweights
                     and Silicon Valley's folk hero.


3. Ray Flournoy, a long time CSLI affiliated grad student, will be
giving his oral defense on Friday, pleas


	     Automatic Acquisition of Pronunciation Rules
		     Using Error-Driven Learning
			Raymond Suke Flournoy
		    Department of Computer Science
			 Stanford University
		   Friday, 12 November 1999, 4:30pm
			 Ventua Hall, Rm. 17

The development of error-driven learning, also known as
transformation-based learning or Brill's algorithm, was an important
landmark in part-of-speech (POS) tagging research, because it showed
that very good tagging results could be attained with simple training
and almost no human intervention.  Its results were equivalent to much
more labor-intensive systems which were based on human-encoded rules
and grammars.  In this work, I show how error-driven learning can be
adapted and generalized to apply to grapheme-phoneme conversion (GPC),
the task of determining the pronunciation of written words.  After
describing the fundamental differences between POS tagging and GPC
which keep us from applying error-driven learning directly, I describe
how to adapt the approach to handle these differences and I then give
some experimental results.  In addition, I discuss how a number of
other tasks within Natural Language Processing can also be handled by
this generalized form of error-driven learning.