NATURAL LANGUAGE PROCESSING

By SARAH ANDERSON

DOCUMENT ROUTING IS IN TURN RELATED TO THE TASK OF DOCUMENT CLASSI?CATION (SEE CHAPTER 4) IN THIS TASK, WE ARE CONCERNED WITH ASSIGNING DOCUMENTS TO CLASSES, USUALLY BASED UPON THEIR CONTENT IN THE MOST GENERAL CASE, A DOCUMENT COULD BE ASSIGNED TO MORE THAN ONE CLASS, AND THE CLASSES COULD BE PART OF SOME LARGER STRUCTURE, SUCH AS A SUBJECT HIERARCHY IT IS POSSIBLE TO DISTINGUISH THIS AC- TIVITY FROM DOCUMENT INDEXING, WHERE WE WOULD LIKE A PROGRAM TO AUTOMATICALLY ASSIGN SELECTED KEYWORDS OR PHRASES TO A DOCUMENT, E G , TO BUILD A ‘BACK OF THE BOOK’ STYLE INDEX SOMETIMES THE FOCUS IS NOT UPON ?NDING THE RIGHT DOCUMENT, BUT UPON ?NDING SPECI?C INFORMATION TARGETS IN A DOCUMENT OR SET OF DOCUMENTS FOR EX- AMPLE, GIVEN A SET OF NEWS ARTICLES ABOUT CORPORATE TAKEOVERS, YOU MIGHT WANT TO DISTIL, FROM EACH ARTICLE, WHO BOUGHT WHOM THIS IS USUALLY CALLED INFORMA- TION EXTRACTION, AND IT PROVIDES A WAY OF GENERATING VALUABLE METADATA16 THAT WOULD OTHERWISE REMAIN BURIED INSIDE A DOCUMENT COLLECTION (SEE CHAPTER 3) AT LEAST SOME FORMS OF DOCUMENT SUMMARIZATION CAN BE REGARDED AS A SPECIAL KIND OF INFORMATION EXTRACTION, IN WHICH A PROGRAM ATTEMPTS TO EXTRACT THE SALIENT INFORMATION FROM A DOCUMENT AND PRESENT IT AS A SURROGATE DOCUMENT