Dear colleagues,
Following the suggestion of Jimmy Wales, we would like to announce a new paper
that uses Wikipedia as a very large-scale repository of world knowledge
for information retrieval tasks. To date, Wikipedia was mostly used by human
users
(readers), and we hope our research opens a promising new direction of
automatically
using the knowledge from Wikipedia for tasks that normally require human-level
intelligence. In our ongoing research, we plan to explore using Wikipedia for
additional text processing tasks, such as Web search and word sense
disambiguation.
Evgeniy Gabrilovich and Shaul Markovitch (2006).
''Overcoming the Brittleness Bottleneck using Wikipedia:
Enhancing Text Categorization with Encyclopedic Knowledge''.
Proceedings of the 21st National Conference on Artificial Intelligence
(AAAI-06), pp. 1301-1306.
http://www.cs.technion.ac.il/~gabr/papers/wiki-aaai06.pdf
Kind regards,
Evgeniy.
--
Evgeniy Gabrilovich
Ph.D. student in Computer Science
Department of Computer Science, Technion - Israel Institute of Technology
Technion City, Haifa 32000, Israel
Email: gabr(a)cs.technion.ac.il WWW:
http://www.cs.technion.ac.il/~gabr