Excercise for Information Extraction - test set

File contents

Testing set

(2)

Try your phrases with following elements
Which of them returned results?
Which did not?
What other patterns were discovered?

Countries:

Indonesia
Georgia
Kuwait
Benin
Monaco
Norhern Ireland
Hong Kong
Canada

-----------------------

(3)

People:

Gene Kelly		Betsy Blair
Kathryn Hays		Glenn Ford
David Furnish		Elton John
Gloria Swanson		William Dufty
Alma Reville		Alfred Hitchcock
George Michael		Kenny Goss

check if your patterns hold on these people pairs

-----------------------

(6)

Testing important people in companies

Xerox
Deutsche Bahn
Wachovia
HP
Wolfram Research

check if your patterns hold for these companies

(6a)

Do recognizing entities as companies work?

If you used Wikipedia categories, can you go from categories to companies?
Try traversing the category tree 
- any starting point and going down?
- where to stop or go to the leaves?