Return-Path: X-Original-To: apmail-ctakes-user-archive@www.apache.org Delivered-To: apmail-ctakes-user-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 9E47610EF7 for ; Wed, 15 Jan 2014 04:35:01 +0000 (UTC) Received: (qmail 36471 invoked by uid 500); 15 Jan 2014 04:35:01 -0000 Delivered-To: apmail-ctakes-user-archive@ctakes.apache.org Received: (qmail 36233 invoked by uid 500); 15 Jan 2014 04:34:55 -0000 Mailing-List: contact user-help@ctakes.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: user@ctakes.apache.org Delivered-To: mailing list user@ctakes.apache.org Received: (qmail 36217 invoked by uid 99); 15 Jan 2014 04:34:53 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 15 Jan 2014 04:34:53 +0000 X-ASF-Spam-Status: No, hits=2.2 required=5.0 tests=HTML_MESSAGE,RCVD_IN_DNSWL_NONE,SPF_PASS X-Spam-Check-By: apache.org Received-SPF: pass (athena.apache.org: domain of cybersation@hotmail.com designates 65.54.51.97 as permitted sender) Received: from [65.54.51.97] (HELO snt0-omc4-s46.snt0.hotmail.com) (65.54.51.97) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 15 Jan 2014 04:34:48 +0000 Received: from SNT148-W51 ([65.55.90.199]) by snt0-omc4-s46.snt0.hotmail.com with Microsoft SMTPSVC(6.0.3790.4675); Tue, 14 Jan 2014 20:34:27 -0800 X-TMN: [lfw54a18Gr0LA/90guS25OCAZhKUsFOQ] X-Originating-Email: [cybersation@hotmail.com] Message-ID: Content-Type: multipart/alternative; boundary="_865140b4-02d4-48c3-93e9-712b478cbe35_" From: digital paula To: "user@ctakes.apache.org" , "dev@ctakes.apache.org" Subject: RE: cTakes: question on updating cue words Date: Tue, 14 Jan 2014 23:34:27 -0500 Importance: Normal In-Reply-To: References: ,<924DE05C19409B438EB81DE683A942D91061D9F6@CHEXMBX1A.CHBOSTON.ORG>,,<52AF6CBD.302@childrens.harvard.edu>,,,,,,, MIME-Version: 1.0 X-OriginalArrivalTime: 15 Jan 2014 04:34:27.0715 (UTC) FILETIME=[13412530:01CF11AB] X-Virus-Checked: Checked by ClamAV on apache.org --_865140b4-02d4-48c3-93e9-712b478cbe35_ Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Hello again=2C I've been busy with figuring out the issue with sectionizer= and had forgot about this...still haven't received a response. :-( I rea= lly hope Matt or anyone familiar with cue word updates can help. =20 Developers/users should be able to update cue words because it can be subj= ective as to what category a cue word may fall in. For example=2C 'predic= tive of' could be a negation or uncertainty depending on the task of takin= g current or future state into consideration. There are several cue terms= in the cue term files that I'd like to change their assignment. =20 =20 Who determines what gets classified as negation or speculation and so forth= ? Is it a committee? I really hope someone can explain more on the cue.mo= del and what I stated in previous email. =20 =20 Thanks.=20 =20 Regards=2C Paula =20 From: cybersation@hotmail.com To: user@ctakes.apache.org=3B dev@ctakes.apache.org Subject: RE: cTakes: question on updating cue words Date: Tue=2C 7 Jan 2014 13:36:33 -0500 =0A= =0A= =0A= =0A= =0A= =0A= Hi Matt=2C =20 I realized that I should have posted this on the developer site. =20 First of all=2C thanks for your followup a few weeks back. I hadn't been s= ubscribed to the developer list prior to your post so I didn't see it until= Pei mentioned it. =20 Not sure if you saw my response on user list but I wasn't able to get your = suggestion to work so I defaulted back to what I was trying to do with upda= ting the medfacts snapshot jar. After stepping through the code I see that= cTAKES was identifying the new cue term from the updated medfacts snapshot= jar (I had decompiled the jar=2C added the new term 'predictive of'=2C the= n added jar back to cTAKES). Okay=2C so cTAKES did identify the new cue te= rm but it's not getting allocated to the 'possible' assertion type. Since= last night I've looked at several of the java files in the medfacts jar an= d quickly realized that UIMA is not just the foundation of cTAKES=2C MITRE = is too! =20 =20 I would love to understand how does the cue word type(i.e. 'predictive of')= get associated to the assertion type(i.e. 'possible')? I can't seem to= figure that out by looking at the code in the medfacts jar. I'd like to= understand how I can update it so my new cue word gets recognized as a 'po= ssible' assertion type. The existing words in the speculation are gettin= g the correct 'possible' associate type. Just the new cue term I added def= aults to 'present'. This leads me to wonder if it's the cue.model that's= doing the assignment and has to be updated to recognize new cue word. I'= m hoping you can elucidate further on what the cue.model file is and how it= works. It appears to be a binary of some type. What tools would be need= ed to update it? Hmmm=2C the fact that it's a .model extension leads me = to believe that it's the result of some hefty machine learning that's conta= ined in that cue.model file. =20 =20 Thanks so much. =20 Regards=2C PaulaFrom: cybersation@hotmail.com To: user@ctakes.apache.org Subject: RE: cTakes: question on updating cue words Date: Sun=2C 5 Jan 2014 21:38:55 -0500 =0A= =0A= =0A= Happy New Year cTAKES Community! Hopefully everyone's staying warm. =20 Okay=2C I did try Matt's suggestion from developer site http://mail-archives.apache.org/mod_mbox/ctakes-dev/201312.mbox/%3cCED4DCCB= .126B0%25mcoarr@mitre.org%3e =20 but unfortunately it didn't work so I just stepped through the code to see= what's going on with how cue words are being used in cTAKES. I verified = that the medfacts snapshot jar that contains around 30 txt files for cue w= ords are all being called. So before I tried Matt's recent suggestion I d= id decompile the medfacts snapshot jar and add the new cue terms to the jar= then added it back to cTAKES.... thought it wasn't being recognized but it= is. I had updated the speculation text file with 'predictive of' as a new= cue term and while stepping through I see that 'predictive of' was recogni= zed as a cue term from the speculation file. =20 =20 The problem is that it gets annotated as 'present' not as 'possible'. Tha= t's why I thought the updated cue term wasn't being recognized. I did a qu= ick test using one of the already stated terms(I used 'improbable') from th= e speculation text file and sure enough the same file that contains the new= cue term of 'predictive of' got annotated as 'possible' which has me wonde= ring about the cue model and how it gets generated. =20 =20 So to echo what Tim stated=2C what does the cue model do? What exactly is = that file and how can the contents be viewed and regenerated or updated? = Something clearly has to be updated so 'predictive of' gets annotated as 'p= ossible'. =20 =20 I'm so close to getting this resolved so I would appreciate any assistance. =20 Thanks. =20 Regards=2C Paula =20 From: Timothy.Miller@childrens.harvard.edu To: user@ctakes.apache.org Subject: Re: cTakes: question on updating cue words Date: Tue=2C 24 Dec 2013 14:19:46 +0000 =0A= =0A= =0A= =0A= =0A= Actually=2C I think Matt's suggestion is a bit out of date -- during develo= pment we removed the dependency on the lucene dictionary lookup and now the= under development version does read those psv files directly.=0A= =0A= =0A= But this still doesn't help Paula since she's trying to run the current rel= ease. I thought Matt or Pei might have some info about whether its possible= to modify negation cue words for that release? For example=2C I can see in= the code it uses a "cue model" which=0A= can be found in ctakes-assertion-res but it is a binary and I'm not sure w= hat kind. Is there any way to modify that file? =0A= =0A= Tim =0A= =0A= =0A= On 12/24/2013 12:09 AM=2C digital paula wrote: =0A= =0A= =0A= Thank you=2C Pei. I believe I had signed up for the dev list right after M= att posted so I didn't see his email. I will try it out.=20 =0A= =20 =0A= Merry Christmas to you and everyone on the list. :-) =0A= =20 =0A= Regards=2C =0A= Paula =0A= =20 =0A= =0A= =0A= Date: Mon=2C 23 Dec 2013 23:42:30 -0500 =0A= Subject: Re: cTakes: question on updating cue words =0A= From: chenpei@apache.org =0A= To: user@ctakes.apache.org =0A= =0A= Paula=2C=0A= Were you able to try Matt's suggestion on dev@?=0A= http://mail-archives.apache.org/mod_mbox/ctakes-dev/201312.mbox/%3cCED4DCCB= .126B0%25mcoarr@mitre.org%3e =0A= =0A= =0A= =0A= =0A= =0A= =0A= On Mon=2C Dec 23=2C 2013 at 11:57 AM=2C digital paula =0A= wrote: =0A= =0A= =0A= Hello again cTAKES Community=2C =0A= =20 =0A= I think Tim's away for the holidays since I didn't see any response. Cou= ld someone else assist? To reiterate=2C I'd like to manually update the cu= e words for the polarity and uncertainty features. Please see below for= details. =0A= =20 =0A= Thanks. =0A= =20 =0A= Regards=2C =0A= Paula =0A= =0A= =20 =0A= =0A= =0A= From: =0A= cybersation@hotmail.com =0A= To: =0A= user@ctakes.apache.org=0A= =0A= Subject: RE: cTakes: question on updating cue words =0A= =0A= Date: Thu=2C 19 Dec 2013 16:20:25 -0500=0A= =0A= =0A= =0A= Hi Tim=2C I just realized that my manual cue word updates didn't take. := -( =0A= =20 =0A= I updated these two files from the med-facts.i2b21.2-SNAPSHOT.jar=2C then r= ebundled and added back to cTAKES: =0A= 1. negation_cue_list.txt =0A= 2. certainty.txt =0A= =20 =0A= Is there another file that you know of that needs to be updated? In the = cue folder under the jar contains only text files perhaps there's another t= ext file I need to update=2C would you know what the files would be or what= other updates need to be made? =0A= =0A= =0A= Thanks. =0A= =20 =0A= Regards=2C =0A= Paula =0A= =0A= =0A= Date: Mon=2C 16 Dec 2013 16:12:29 -0500 =0A= From: =0A= timothy.miller@childrens.harvard.edu =0A= To: =0A= user@ctakes.apache.org =0A= Subject: Re: cTakes: question on updating cue words =0A= =0A= Paula=2C I think to use the released version of ctakes you will have to do = what you proposed - modify the jar. The checked in files (*.psv) that you a= re finding are for the under-development version. =0A= Tim =0A= =0A= =0A= On 12/16/2013 03:27 PM=2C digital paula wrote: =0A= =0A= =0A= Hi Pei=2C =0A= =20 =0A= I don't consider this a bug so not sure why a jira ticket is needed=2C I ju= st need to add 2 cue words wondering if I can do it manually? =0A= =0A= =20 =0A= Exploring a bit=2C I see there are .psv files in Assertion component in the= Cue_Words folder that I updated but it doesn't seem to work. I also adde= d to the Semantic_Classes folder (in Assertion as well)=2C the cue words in= the .txt file and that didn't work=0A= either. =20 =0A= =20 =0A= One thing that I haven't tried is updating the cue words in the org.mitre.m= edfacts.i2b2.cuefiles package for the jar file: medfacts-i2b2-1.2.SNAPSHPO= T.jar. That would be a little more work since I need to extract and rebuil= d jar file and add back to project.=0A= =0A= =20 =0A= I'm kind of on a huge deadline and hoping I can make these changes today so= hoping this doesn't require a lot of time to just add a couple cue words. =0A= =20 =0A= By the way=2C was is a .psv file? =20 =0A= =20 =0A= Thanks. =0A= =20 =0A= Regards=2C =0A= Paula =0A= =20 =0A= =0A= =0A= From: =0A= Pei.Chen@childrens.harvard.edu =0A= To: =0A= dev@ctakes.apache.org =0A= Subject: RE: cTakes: question on updating cue words =0A= Date: Mon=2C 16 Dec 2013 19:31:45 +0000 =0A= =0A= [moved to dev@] =0A= Hi Paula=2C =0A= My suggestion would be to open a Jira item so=0A= that it could be tracked: =0A= https://issues.apache.org/jira/browse/CTAKES (Feel free to create a new acc= ount). =0A= Even cooler if you could attach the affected files with the patch(diffs) an= d any tests. =0A= --Pei =0A= =20 =0A= =20 =0A= =0A= =0A= =0A= From:=0A= digital paula [mailto:cybersation@hotmail.com]=0A= =0A= Sent: Monday=2C December 16=2C 2013 1:30 PM =0A= To: =0A= user@ctakes.apache.org =0A= Subject: cTakes: question on updating cue words =0A= =0A= =0A= =20 =0A= Hello again cTAKES Community=2C =0A= =20 =0A= I would like to add additional cue words to polarity (for negation) and un= certainty. I would so appreciate if someone can let me know how I can ad= d additional cue words. =0A= =0A= =20 =0A= Thanks. =0A= =20 =0A= Regards=2C =0A= Paula=20 =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= =0A= = --_865140b4-02d4-48c3-93e9-712b478cbe35_ Content-Type: text/html; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable
Hello again=2C =3B I've been=  =3Bbusy with figuring out the issue with sectionizer =3Band had fo= rgot about this...still haven't received a response. =3B :-( =3B I = really hope Matt or anyone familiar with cue word updates can =3Bhelp.<= BR> =3B
Developers/users =3Bshould be able to =3B =3Bupd= ate cue words because =3Bit can be subjective as =3Bto what categor= y =3Ba cue word may fall in. =3B For example=2C =3B 'predictive= of' =3B =3Bcould =3Bbe a negation or uncertainty depending on = the task of taking current or future state into consideration. =3B &nbs= p=3BThere are several =3Bcue terms =3Bin the cue term files that I'= d like to change their assignment. =3B =3B
 =3B
Who dete= rmines what gets classified as negation or speculation and so forth? = =3B Is it a committee?  =3BI really hope someone can explain more on th= e cue.model and what I stated in previous email. =3B
 =3B
Th= anks.
 =3B
Regards=2C
Paula
 =3B
From: cybersation@hotmail.com
To: user@ctakes.apache.org=3B d= ev@ctakes.apache.org
Subject: RE: cTakes: question on updating cue words=
Date: Tue=2C 7 Jan 2014 13:36:33 -0500

=0A= =0A= =0A=
=0A= =0A= =0A=
Hi Matt=2C
 =3B
I =3Brealized that I should = have posted this on the developer site.
 =3B
First of all=2C than= ks for your =3Bfollowup a few weeks back. =3B I hadn't =3Bbeen = subscribed to the developer list prior to your post =3Bso I didn't see = it until Pei =3Bmentioned it.
 =3B
Not sure =3Bif you saw= my response on user list but I wasn't able to get your suggestion to work = so I defaulted back to what I was trying to do with updating the medfacts s= napshot jar. =3B After stepping through the code I see that =3BcTAK= ES was identifying the =3Bnew =3Bcue term from the updated medfacts= snapshot jar (I had decompiled the jar=2C added the new term 'predictive o= f'=2C then added jar back to cTAKES). =3B Okay=2C so cTAKES did identif= y the new cue term =3Bbut it's not =3Bgetting allocated to the 'pos= sible' =3Bassertion type. =3B =3B =3BSince last night I've&= nbsp=3Blooked at several of the java files in the medfacts jar and =3Bq= uickly realized that UIMA is not just the =3Bfoundation of cTAKES=2C MI= TRE is too! =3B =3B
 =3B
I would love to understand how = does the cue word type(i.e. 'predictive of') =3Bget associated to the a= ssertion type(i.e. 'possible')? =3B =3B =3B =3B I can't see= m to figure that out by looking at the code in the medfacts jar. =3B&nb= sp=3B =3B I'd like to understand how I can update it so my new cue = =3Bword gets recognized as a 'possible' assertion type. =3B =3B&nbs= p=3B The =3Bexisting words in the speculation are getting the correct '= possible' associate type. =3B Just the new =3Bcue term I added defa= ults to 'present'. =3B =3B =3B =3BThis leads me to wonder i= f it's the cue.model that's doing the assignment and has to be updated to r= ecognize new cue word. =3B =3B I'm hoping you can elucidate further= on what the cue.model file is and how it works. =3B It appears to be a= binary of some type. =3B =3B What tools would be needed to update = it? =3B =3B Hmmm=2C =3B the fact that it's a .model extension l= eads me to believe that it's the result of some hefty machine learning that= 's =3Bcontained in that cue.model file. =3B
 =3B
Thanks = so much.
 =3B
Regards=2C
Paula
From:= cybersation@hotmail.com
To: user@ctakes.apache.org
Subject: RE: cTak= es: question on updating cue words
Date: Sun=2C 5 Jan 2014 21:38:55 -050= 0

=0A= =0A=
=0A=
Happy New Year cTAKES Community! Hopefully everyone's stay= ing warm.
 =3B
Okay=2C I did try Matt's suggestion =3Bfrom&nb= sp=3Bdeveloper site
http://mail-archives.apache.org/mod_mbox/ctakes-dev/201312.mbox/%3= cCED4DCCB.126B0%25mcoarr@mitre.org%3e
 =3B
 =3Bbut unfort= unately it didn't work so I just =3Bstepped through the code to see wha= t's going on with how cue words are being used in cTAKES. =3B =3B&n= bsp=3BI verified that the medfacts =3Bsnapshot jar that contains = =3B around 30 =3Btxt files for cue words are all being called. =3B&= nbsp=3B =3BSo before I tried Matt's recent suggestion I did decompile t= he medfacts snapshot jar and add the new cue terms to the jar then added it= back to cTAKES.... thought it wasn't being recognized but it is. =3B&n= bsp=3BI =3Bhad updated the speculation text file with 'predictive of' a= s a new cue =3Bterm =3Band while stepping through I see that 'predi= ctive of' =3Bwas recognized as a cue term from the speculation file.&nb= sp=3B
 =3B
The problem is that =3Bit gets annotated as 'pres= ent' not as 'possible'. =3B =3B =3BThat's why I thought the upd= ated cue term wasn't being recognized. =3B I did a quick test using one= of the already stated terms(I used 'improbable') from the speculation text= file and sure enough the same file that contains the new cue term of 'pred= ictive of' got annotated as 'possible' which has =3Bme wondering about = the cue model and how =3Bit gets generated. =3B =3B
 =3B=
So to echo what Tim stated=2C what does the cue model do? =3B What = exactly is that file and how can =3Bthe contents be =3Bviewed and r= egenerated or updated? =3B =3B =3BSomething clearly has to be u= pdated so 'predictive of' gets annotated as 'possible'. =3B
 = =3B
I'm so close to getting this resolved so I would appreciate any assi= stance.
 =3B
Thanks.
 =3B
Regards=2C
Paula
 = =3B
From: Timothy.Miller@childrens.harva= rd.edu
To: user@ctakes.apache.org
Subject: Re: cTakes: question on up= dating cue words
Date: Tue=2C 24 Dec 2013 14:19:46 +0000

=0A= =0A= =0A= =0A= =0A=
Actually=2C I think Matt's suggestion is = a bit out of date -- during development we removed the dependency on the lu= cene dictionary lookup and now the under development version does read thos= e psv files directly.=0A=
=0A=
=0A= But this still doesn't help Paula since she's trying to run the current rel= ease. I thought Matt or Pei might have some info about whether its possible= to modify negation cue words for that release? For example=2C I can see in= the code it uses a "cue model" which=0A= can be found in ctakes-assertion-res but it is a binary and I'm not sure w= hat kind. Is there any way to modify that file?
=0A=
=0A= Tim
=0A=
=0A=
=0A= On 12/24/2013 12:09 AM=2C digital paula wrote:
=0A=
=0A=
=0A=
Thank you=2C Pei. =3B I =3Bbelieve I had signed&nb= sp=3Bup for =3Bthe dev list right after =3BMatt posted so I didn't&= nbsp=3Bsee his =3Bemail. =3B I will try it out. =3B
=0A=  =3B
=0A= Merry Christmas to you and everyone on the list. =3B :-)
=0A=  =3B
=0A= Regards=2C
=0A= Paula
=0A=  =3B
=0A=
=0A=
=0A= Date: Mon=2C 23 Dec 2013 23:42:30 -0500
=0A= Subject: Re: cTakes: question on updating cue words
=0A= From: chenpei@apache.org
=0A= To: user@ctakes.apache.org
=0A=
=0A=
Paula=2C=0A=
Were you able to try Matt's suggestion on dev@?
=0A= =0A=

=0A=
=0A=
=0A=

=0A=
=0A=
On Mon=2C Dec 23=2C 2013 at 11:57 AM=2C digit= al paula =0A= <=3Bcybersat= ion@hotmail.com>=3B wrote:
=0A=
=0A=
=0A=
Hello again =3BcTAKES Community=2C
=0A=  =3B
=0A= I think Tim's away for the holidays since I didn't see any =3B response= .  =3B =3BCould someone else assist? =3B =3BTo reiterate=2C= I'd like to manually update the cue words for =3Bthe polarity and unce= rtainty features. =3B =3B =3B =3B Please see below for deta= ils.
=0A=  =3B
=0A= Thanks.
=0A=  =3B
=0A= Regards=2C
=0A= Paula
=0A=
=0A=  =3B
=0A=
=0A=
=0A= From: =0A= cybersation@hotmail.com
=0A= To: =0A= user@ctakes.apache.org=0A=

=0A= Subject: RE: cTakes: question on updating cue words
=0A=
=0A= Date: Thu=2C 19 Dec 2013 16:20:25 -0500=0A=
=0A=

=0A=
=0A=
Hi Tim=2C =3B I just realized =3Bthat my manual cu= e word updates didn't take. =3B =3B :-(
=0A=  =3B
=0A= I updated these two files from the med-facts.i2b21.2-SNAPSHOT.jar=2C then&n= bsp=3Brebundled and added back to cTAKES:
=0A= 1. =3B negation_cue_list.txt
=0A= 2. =3B certainty.txt
=0A=  =3B
=0A= Is there another file that you know of that needs to be updated? =3B&nb= sp=3B =3B In the cue folder under the jar contains only text files perh= aps there's another text file I need to update=2C would you know what the f= iles would be or what other updates need to be made? =3B=0A=
=0A=
=0A=  =3BThanks.
=0A=  =3B
=0A= Regards=2C
=0A= Paula
=0A=
=0A=
=0A= Date: Mon=2C 16 Dec 2013 16:12:29 -0500
=0A= From: =0A= timothy.miller@childrens.harvard.edu
=0A= To: =0A= user@ctakes.apache.org
=0A= Subject: Re: cTakes: question on updating cue words
=0A=
=0A= Paula=2C I think to use the released version of ctakes you will have to do = what you proposed - modify the jar. The checked in files (*.psv) that you a= re finding are for the under-development version.
=0A= Tim
=0A=
=0A=
=0A=
On 12/16/2013 03:27 PM=2C digital paula wrote:
=0A=
=0A=
=0A=
Hi Pei=2C
=0A=  =3B
=0A= I don't consider this a =3Bbug so not sure why a jira ticket is needed= =2C =3BI just =3Bneed to add 2 cue words wondering if I can =3B= do it manually? =3B=0A=
=0A=  =3B
=0A= Exploring a bit=2C I see there are =3B.psv files in =3BAssertion&nb= sp=3Bcomponent in the  =3BCue_Words folder =3Bthat I updated but it= doesn't seem to work. =3B I also added to the Semantic_Classes folder = (in Assertion as well)=2C the cue words in the .txt file and that didn't wo= rk=0A= either. =3B =3B
=0A=  =3B
=0A= One thing that I haven't tried is =3Bupdating the cue words in the org.= mitre.medfacts.i2b2.cuefiles package =3Bfor the jar file: =3B = =3Bmedfacts-i2b2-1.2.SNAPSHPOT.jar. =3B That would be a little more wor= k since I need to extract and rebuild jar file and add back to project.=0A=
=0A=  =3B
=0A= I'm kind of on a huge deadline and hoping =3BI can make these changes&n= bsp=3Btoday so hoping this doesn't =3Brequire a lot of time to just add=  =3Ba couple cue words.
=0A=  =3B
=0A= By the way=2C was is a .psv file? =3B
=0A=  =3B
=0A= Thanks.
=0A=  =3B
=0A= Regards=2C
=0A= Paula
=0A=  =3B
=0A=
=0A=
=0A= From: = =0A= Pei.Chen@childrens.harvard.edu
=0A= To: =0A= dev@ctakes.apache.org
=0A= Subject: RE: cTakes: question on updating cue words
=0A= Date: Mon=2C 16 Dec 2013 19:31:45 +0000
=0A=
=0A=
[moved to dev@]
=0A= Hi Paula=2C
=0A= My suggestion would be to open a Jira item = so=0A= that it could be tracked:
=0A= = https://issues.apache.org/jira/browse/CTAKES (Feel free to create a new= account).
=0A= Even cooler if you could attach the affected files with the patch(diffs) an= d any tests.
=0A= --Pei
=0A=  =3B
=0A=  =3B
=0A=
=0A=
=0A=
=0A= From:=0A= digital paula [mailto:cybersation@hotmail.com]=0A=
=0A= Sent: Monday=2C December 16=2C 2013 1:30 PM
=0A= To: =0A= user@ctakes.apache.org
=0A= Subject: cTakes: question on updating cue words
=0A=
=0A=
=0A=  =3B
=0A=
Hello again c= TAKES Community=2C
=0A=  =3B
=0A= I would like to =3B add additional cue words =3Bto =3Bpolarity = (for negation) =3Band uncertainty. =3B =3B =3B I would so a= ppreciate if someone can let me know how I can add additional cue words.&nb= sp=3B =3B =3B=0A=
=0A=  =3B
=0A= Thanks.
=0A=  =3B
=0A= Regards=2C
=0A= Paula
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
=0A=
= --_865140b4-02d4-48c3-93e9-712b478cbe35_--