Mailing-List: contact notifications-help@ctakes.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@ctakes.apache.org
Date: Tue, 24 Nov 2015 21:04:10 +0000 (UTC)
From: "Omkar Natu (JIRA)" <jira@apache.org>
To: notifications@ctakes.apache.org
Message-ID: <JIRA.12914508.1447946851000.181926.1448399050957@Atlassian.JIRA>
In-Reply-To: <JIRA.12914508.1447946851000@Atlassian.JIRA>
References: <JIRA.12914508.1447946851000@Atlassian.JIRA>
 <JIRA.12914508.1447946851820@arcas>
Subject: [jira] [Commented] (CTAKES-390) problem in detecting a family
 memeber
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/CTAKES-390?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15025399#comment-15025399 ] 

Omkar Natu commented on CTAKES-390:
-----------------------------------

As per your issue I did not get subject = "family member" when I tested for "dad has diabetes". can you provide any details. subject = "patient" in either case for me. can you provide the details of version and also the files other than SubjectClassifier you fixed (if any )

> problem in detecting a family memeber
> -------------------------------------
>
>                 Key: CTAKES-390
>                 URL: https://issues.apache.org/jira/browse/CTAKES-390
>             Project: cTAKES
>          Issue Type: Bug
>          Components: ctakes-assertion
>    Affects Versions: 3.2.2
>            Reporter: alina shapira
>   Original Estimate: 10m
>  Remaining Estimate: 10m
>
> when parsing a sentence including a family member, the family member not detected  if it does not appear as the first word in the sentence.
> so in "dad ha diabetes" the subject is found to be a family member
> but in "his dad has diabetes" the subject is the patient himself.
> looks related to the  SubjectAttributeClassifier class
> in function  isFamilyTerm(Annotation arg) 
> need to change the matches statement so that the family keyword may appear not as a first word:
>    .matches(".*(father|dad|mother|mom|bro|sis|sib|cousin|aunt|uncle|grandm|grandp|grandf|"    "wife|spouse|husband|child|offspring|progeny|son|daughter|nephew|niece|kin|family).*");


--
This message was sent by Atlassian JIRA
(v6.3.4#6332)