You are viewing a plain text version of this content. The canonical link for it is here.

Posted to user@ctakes.apache.org by Anirban Chakraborti <ch...@googlemail.com> on 2014/05/01 19:41:12 UTC

Parsing the output of Ctakes

I am new to Ctakes and I have used the CVD for annotating free text into
UMLS concepts.

The output is huge and I am only interested in the SNOMED,
RXnorm , Lab concepts .

How do I handle the output so that I can get only the objects of interest.
Also often the SNOMED concepts are two level deep for one identified
object. What does it mean.

Please help

Anirban

Re: Parsing the output of Ctakes

Posted by John Green <he...@gmail.com>.

I like lxml for python bc what most of what I do does not require heavy support code. 


JG
—
Sent from Mailbox for iPhone

On Thu, May 1, 2014 at 1:45 PM, Anirban Chakraborti
<ch...@googlemail.com> wrote:

> I am new to Ctakes and I have used the CVD for annotating free text into
> UMLS concepts.
> The output is huge and I am only interested in the SNOMED,
> RXnorm , Lab concepts .
> How do I handle the output so that I can get only the objects of interest.
> Also often the SNOMED concepts are two level deep for one identified
> object. What does it mean.
> Please help
> Anirban