Humans are creative thinkers, but
slow and inefficient processors of information. Businesses that can leverage computing
technology to process this information more quickly and efficiently should reap
a competitive advantage in the marketplace. Manually converting existing textual
data into the relations and data structures of today??™s e-business applications or into
the knowledge networks of tomorrow??™s Semantic Web is, again, a costly enterprise
for humans. Thus, artificial intelligence, machine learning, and other unconventional
approaches must be employed to automatically extract facts from existing Web texts
and convert them to portable formats that conventional software tools can process.
We show that, from documents in a specific domain, where specific types of facts
appear in somewhat regular textual forms, natural language processing techniques
can be effectively used to extract relevant facts and convert them into XML. Our
work adds to a growing body of research establishing the increasing role information
extraction can play in developing competitive e-business services.
Pages:
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277