I have a lot of data and manually extracted annotations for the text. I was looking for any advice to automate the annotation extraction up to a good level of accuracy. Any advice is welcome.

  • $\begingroup$ Read about information extraction and Markov logic networks (python implementation) $\endgroup$
    – Emre
    Jun 29 '17 at 1:01
  • $\begingroup$ It would help if you could provide an example. $\endgroup$
    – gchaks
    Jun 29 '17 at 16:09
  • $\begingroup$ I have a lot of medical data and one particular symptom manually extracted from all of them. I want to automate this process. $\endgroup$ Jun 29 '17 at 17:35

There is a spectrum of methods. On one end is the tried n' true method of performing pattern matching with rules. Write a series of regular expressions (i.e., regex). On the other end is the newer methods of weak supervision, a system that learns over time to get better. Snorkel one of implementation of weak supervision. Here are some snorkel demos.


Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.