AI Seminar
  -------------------------------
  Tuesday, January 18th, 2005
  4:00 pm - 5:30 pm
  175 ATL (Large Conference Room)

  "Machine Translation = Automata Theory + Probability Theory + Linguistics"

  Kevin Knight
  Information Sciences Institute
  University of Southern California

===============================



Recently, machine translation (MT) systems have become much more accurate.
A major reason is that machines now gather translation knowledge
autonomously, combing through large amounts of human-translated material
available on the web. What the systems learn are essentially finite-state
Markov models -- target sub-strings are substituted for source sub-strings,
followed by some re-ordering.  A serious weakness, however, is that this
kind of model can only support very weak linguistic transformations, and
the trained models do not yet lead to reliably high-quality MT.

Over the past three years, many new probabilistic tree-based (versus
string-based) models have been designed and tested on many natural language
applications, including MT.  Most of these models turn out to be instances
of tree transducers, a formal automata model first described by W. Rounds
and J. Thatcher in the 1960s and 70s.  These automata open up new
opportunities for us to marry deeper representations, automata theory, and
machine learning.  This talk will cover new learning algorithms for tree
automata, together with experiments in machine translation.


Bio: Kevin Knight is a Senior Research Scientist at USC's Information
Sciences Institute, a Research Associate Professor in the Computer Science
Department at USC, and a founder of Language Weaver, Inc.  He received his
Ph.D. from Carnegie Mellon University in 1991 and his BA from Harvard
University in 1986.  He is co-author (with Elaine Rich) of the textbook
"Artificial Intelligence".  His main research interests are statistical
natural language processing, machine translation, natural language
generation, and decipherment.  Dr. Knight is serving as General Chair of
the Association for Computational Linguistics conference to be held this
year at the University of Michigan.