I reiterate I think that ctakes should integrate dirk's repository. Ill write up a brief overview on how to set up a very simple host/guest network deploying his wrapper around ctakes, giving it a friendly json output from http/post queries using the umls/fast pipeline. Jg
On March 10, 2017 at 14:49:32 MST, Alden Gordon <[email protected]> wrote:This is great - thanks, James. Are the commands in the hackphlet meant to be run in a bash shell? They don't seem to work on the windows command line. @Hephaestus Studio - Thanks for the tip here. Do you have experience setting up this package? As such a rookie I'm running into a lot of technical difficulties - specifically he says to run the mvn package, which doesn't seem to appear in the repository. Additionally, does anyone have thoughts on why the Aggregate Plaintext UMLS processor would not provide negation or concept codes? I've tried it with both the CVD and CPE. Apologies for the barrage of questions, but I appreciate everyone's support here. On Thu, Mar 9, 2017 at 12:41 PM, James Masanz <[email protected]> wrote:I've posted the pamphlet/manual to the Wiki for 3.2.2. https://cwiki.apache.org/confluence/download/attachments/44302415/cTAKES.Hackphlet.3.2.2.pdf On Thu, Mar 9, 2017 at 11:50 AM, James Masanz <[email protected]> wrote:I'm making some minor changes to the pamphlet Guergana mentioned and will send it out or post it later today. On Wed, Mar 8, 2017 at 5:03 PM, Savova, Guergana <[email protected]> wrote: Yes, we have a guide (aka pamphlet) with a description of the cTAKES basics. We will be distributing it with the 4.0 release targeted at the end of the month. Sean Finan might be able to distribute the pamphlet now… --Guergana From: Kevin B. Cohen [mailto:[email protected]] Sent: Wednesday, March 8, 2017 4:27 PM To: [email protected] Subject: Re: Named entity recognition Alden, if you find such a beginner's guide and could distribute its whereabouts to the rest of us, it would be great. Kevin On Tue, Mar 7, 2017 at 6:39 PM, Alden Gordon <[email protected]> wrote: Does anyone have a beginners guide to applying cTAKES named entity recognition to a corpus? I have used the aggregate plain text processor with the collection process engine on my data (the text of a PCP - specialist curbside consult), but it seems to only capture capitalization and part of speech. I would like to capture negation and assign relevant words to SNOMED concepts. Thank you in advance for any general guidance. Additionally, if anyone has any advice on using cTAKES with python, I would appreciate the help Best, Alden -- Alden Gordon Analytics Lead | 860.402.6572 | [email protected] Visit Care Without Constraints to learn how eConsults are removing barriers to care. -- Kevin Bretonnel Cohen, PhD Director, Biomedical Text Mining Group Computational Bioscience Program, U. Colorado School of Medicine Chair in Natural Language Processing for the Biomedical Domain Université Paris-Saclay, LIMSI-CNRS 303-916-2417 http://compbio.ucdenver.edu/Hunter_lab/Cohen -- Alden Gordon Analytics Lead | 860.402.6572 | [email protected] Visit Care Without Constraints to learn how eConsults are removing barriers to care.
