What exactly do you mean by information extraction ?
do you want to extract the existing content into any pattern of your choice or you are looking for any summarized information of that document/content ? where automated knowledge will be found ?
First of all, thank you for caring and about my Q.
I meant Text recognition because I'll use it on a bench of PDF files that I've already. I'm searching now about the use of deep learning on detection on semantic text or something like that.
Thank you for answering. I'm looking to extract the existing content.
for example : Extracting Author name from article (Journal, Conference) as you know there is no unified form and journals write authors names with different styles and at different places
For complementing the answer provided by M. J. Ebadi within the algorithmic point of view, I recommend to review the algorithm proposed in:Article Information extraction from research papers using conditiona...
Where they use CRFs to efficiently extract information from documents.