Information extraction from text, Week 6

The solutions should be ready for inspection by Friday 28.3.2002 (midnight).

Remember that always, if you are in doubt what you should do, you can ask Lili or send a message to our newsgroup!!

1. Describe the wrapper generation algorithm (section 4.1.) of the RoadRunner method using the two HTML pages which you find here.

   The article: Crescenzi, Mecca, Merialdo: RoadRunner: Towards automatic data extraction from large web sites, Proceedings of the 27th VLDB conference.

2. Write a short summary of the phases of an IE process, both in case of

   • IE from unstructured ("normal" text) and
   • IE from (semi-)structured text (like HTML pages).