I would like to ask if there is a library of regular expressions for mining patterns reflecting lexical semantic relations from a corpus.
These patterns should cover a wide variety of aspects synonymy ("A is a B", "A a.k.a B", "A sometimes called B", ...), hyponymy, and so on.
This could be quite interesting for me, since instead of relying in the mere co-occurence of words in a corpus, I could rely in the existence of patterns assuring the accuracy of the semantic relation.

  • What kind of research did you do already? Pattern based Information extraction is established for quite some time, and there are easily available publications on that topic. Dec 19, 2016 at 15:05
  • Thank you for your reply. You are right. However, most of authors use just a dozen of patterns, and moreover, they describe them using plain language instead of the corresponding regular expressions. Such a library could help me to save a lot of time (and errors) on manually coding all the possible regular expressions. Best regards
    – Jorgemar
    Dec 19, 2016 at 15:18


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.