Mailing-List: contact dev-help@ctakes.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@ctakes.apache.org
From: "Finan, Sean" <Sean.Finan@childrens.harvard.edu>
To: "dev@ctakes.apache.org" <dev@ctakes.apache.org>
Subject: RE: Distributing modifiers across conjunctions
Thread-Topic: Distributing modifiers across conjunctions
Thread-Index: AQHRXd9y/HwJahEWqE24WBSVlkT75p8ZFbRw
Date: Tue, 2 Feb 2016 18:41:57 +0000
Message-ID: <dc2340d887c440b99c205ba6028d03d4@CHEXMAIL1B.CHBOSTON.ORG>
References: <03D94C27-5466-4962-96D6-84FA0E929B4E@ucsf.edu>
In-Reply-To: <03D94C27-5466-4962-96D6-84FA0E929B4E@ucsf.edu>
Accept-Language: en-US
Content-Language: en-US
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0

Hi John,

One thing that you can try is using the "Overlap" version of the dictionary=
 lookup.  It should identify both "right .... lower quadrant pain" and "lef=
t lower quadrant pain" as Sign/Symptoms.

Check https://cwiki.apache.org/confluence/display/CTAKES/cTAKES+3.2+-+Fast+=
Dictionary+Lookup almost at the bottom: "Text Overlap Match"

Sean

-----Original Message-----
From: John Mongan [mailto:john.mongan@ucsf.edu]=20
Sent: Tuesday, February 02, 2016 12:30 PM
To: dev@ctakes.apache.org
Subject: Distributing modifiers across conjunctions

I'm working with some text that has a lot of phrases of the form:

right and left lower quadrant pain

In processing this text, I would like to identify the concepts "right lower=
 quadrant pain" and "left lower quadrant pain", but instead the concepts th=
at get identified are "right" and "left lower quadrant pain"

I've got some ideas about how I could fix this, but wanted to see if this i=
s a problem that others have worked on so I don't unnecessarily reinvent an=
y wheels.

Thanks,

John