is prohibited.
??? Patterns where sales is the last word, with n-1 words before it:
increase of 50% in sales
10% increase in the sales
These patterns help us to generate rules for information extraction. The following
shows a simple rule that FIRST uses to extract information about financial items such
as sales, and their relation to financial status words such as increase or decrease.
Extraction Rule to Identify Financial Status (increase, decrease??¦)
??? Example of a proximity rule for financial status:
Let n1 be the optimal proximity within which a financial item appears before
financial status
Let n2 be the optimal proximity within which a financial item appears after
financial status
for each financial item status keyword
if.
a financial item is present within n1 words before the keyword
or. . . .
financial item is present within n2 words after the keyword
then
consider the keyword as a possible candidate for financial status
end.if
end for
Thus, for the sentence ???sales.declined 42%, to $53.4,??? FIRST fills the slots in the
templte as:
Financial Item: sales
Financial Status: decline
Percentage Change: 42%
Change Description: to $53.
Pages:
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263