Monday, April 23, 2001
Is it possible to estimate the difficulty of creating natural language
applications? This problem is of growing practical and theoretical interest.
One measure of complexity is the number of objects and relations in the domain
of consideration. However, for practical applications, measures of complexity
must take into account accuracy of processing, relationship to world
knowledge, evaluations, etc. The talk surveys initial results in the field
and describes research issues ranging from purely mathematical and linguistic
to technological. As part of the presentation, we will discuss parallel
processing of natural language.
Wlodek Zadrozny is currently working with IBM Research Technical Strategy
Team on new technology directions and technical planning. Until last July,
he managed the Conversational Machines project at IBM T.J. Watson Research
Center. The project aims at inventing key technologies and building Web-based
dialog interfaces for electronic commerce and customer support. Previously,
the Conversational Machines group has built a number of successful prototypes
of conversational telephony systems for telephony banking and directory
assistance.
Wlodek Zadrozny received a Ph.D. in mathematics from Polish Academy of
Sciences. He is a past recipient of the Alexander von Humboldt Fellowship
and Haskell B. Curry Fellowship. He has worked at Watson since 1985 and
published over 50 scientific papers and patents in various areas of computer
science. His current interests include business applications of intelligent
technologies, complexity of natural language systems and theories of context.
For directions to CESTM go to https://www.albany.edu/about_the_university/maps/uptown.html.
For additional information call (518) 442-3332.
Center for Environmental Sciences & Technology Management (CESTM) Auditorium
University at Albany
4 p.m. to 6 p.m.
Sponsored by the University at Albany�s Division for Research
Complexity of Natural Language
