News & Events
Topic: Prognostications based on corpus analysis of several hundred million questions
|
Posted - 03/05/2001 : 14:44:22
Language Information Sciences Research Centre
City University of Hong Kong
What's in store for question answering?
Prognostications based on corpus analysis of several hundred million
questions
John B. Lowe
Vice President of Language Engineering and Chief Linguist
Ask Jeeves, Inc.
Time: 11:00 am -- 12:15 pm
Date: May 5, 2001 (Saturday)
Venue: Rm 4428, Mong Man Wai Building, CityU
Abstract
Both the research community and commercial enterprises have set out to
address anew some of the ancient conundrums of question answering and to
answer new challenges posed by the growth of the Internet and its usership.
Successes in the question answering track in TREC and elsewhere have filled
the sails of research and industry projects: novel combinations of NLP and
IR have made it possible to provide in many cases a concise response to
short, factual questions. However, the application of corpus techniques to
the analysis of large query sets provides some sobering data points about
the actual expectations and interests of users of such systems. Initial
results provide food for thought and humbling insights into the linguistic
and computational complexity of the tasks ahead. It is likely that
appropriate responses to many types of questions will remain beyond the
abilities of automatic solutions for some time to come.
Bio Sketch
John Lowe is Vice President of Language Engineering and Chief Linguist at
Ask Jeeves, Inc. After graduating from Yale in 1977, he worked at the
University of California's Office of the President on library planning and
library automation projects, participating in the design and development of
the MELVYL online catalog, UC's MEDLINE implementation, and other online
bibliographic resources. Dr. Lowe received his Ph.D. in linguistics from UC
Berkeley in 1995. His research program at Berkeley included computational
lexicography and computational approaches to the reconstruction of
Sino-Tibetan and Bantu languages. He was a post-doctoral research at the
International Computer Science Institute in Berkeley, developing under
Charles Fillmore the first version of FrameNet, a semantic lexicon of
English.
Enquiries: 2788-9033
___________________ All are welcome! ____________________
|
|
|
Enquiry: LTenquiry@cityu.edu.hk