views:

41

answers:

1

I'd like to read an advertisement for the job through my program. Initially i am working on the templates provided by the microsoft word as "Job Description".

Basically I have to extract the requirements of jobs like required education, skills or any development tools etc. I'd store these requirements in the database and then further use these in my application.

Simply I dont know how to do this efficiently as I'd like to ignore articles, pronouns and so on... I am developing my application in VC#.

+1  A: 

Welcome to NLP. There is a gigantic literature on topic summarization, entity extraction, and other related tasks. It's hard to tell you where to start; there's certainly no simple recipe. There's open source kits that tackle some of the subproblems (e.g. Apache Mahout, Weka), and commercial vendors.

bmargulies
@ bmarguliesCan you pls tell me some of that open source kits...
Kaiynat Naz
I did. Apache Mahout and Weka. But I can also add OpenCRF++ off hand, and Annie/GATE.
bmargulies