Damiano, I just wanted to point out that perhaps you didn't realize that you're posting these questions on the developers' mailing list which is "for development discussions, patch suggestions, and current issues posted to the issue tracker for the project."
There's an OpenNLP users mailing list where you might get better answers from a larger community of practitioners (the first mailing list in https://opennlp.apache.org/mail-lists.html). Cohan On Sat, Sep 24, 2016 at 7:12 PM, Damiano Porta <[email protected]> wrote: > Hello, > we need to categorize our documents in 80 sectors. These documents are > resumes/cv. > > We have many documents (more than 30k) but there is a problem. > Should we try to extract the job positions inside each resume and > categorize them or can we just add the entire document and categorize it in > one or more categories? (max 3 categories) > > I think there is a lof o noising data that can give us many false positives > if we use the entire document. For example, the personal data, hobbies etc > > BUT > > I also know that extract every job position from all the documents will > take years! > > Can anyone give me any workaround ? > > Thank you so much! > Damiano >
