I believe Tim started a thread on how to programmatically extract the entitis/cui's currently via this thread: http://mail-archives.apache.org/mod_mbox/ctakes-dev/201503.mbox/%3ce084d8efe2b03a408b324458c5212e9434c10...@chexmbx3a.chboston.org%3e
A couple of us are going to be in Austin,TX for Apache Con so if you happen to be there, we can plan to meet up. --Pei On Sun, Apr 5, 2015 at 2:51 AM, Abhishek Srivastava <[email protected]> wrote: > I have already searched the archive of this mailing list however if this > question is duplicate then please don't flame me. > > I have some experience with NLTK in Python. I have gone through some of > the basic literature on natural language processing. > > Using NLTK I can perform entity extraction pretty easily. > > My questions are > > 1. is there a tutorial available on CTAKES from a development perspective. > I need to use the API to perform entity extraction. (i need exact APIs). > > 2. How can someone build a custom corpus with CTAKES. I know it works in > medical context but my use case is even narrower (like text related to > gynecology) > > Also, lastly, is there anyone on this mailing list in Dallas region I > would love to meet you in person. > > Regards, > Abhishek. > > > >
