ctakes-vm.apache.org

2014-03-18 Thread Pei Chen
FYI: ASF Infra is setting up our VM for demo purposes. INFRA-7451 If you need access, feel free to let us now. Initial maintainers: james-masanz, andymc,chenpei --Pei

Re: Build from source

2014-03-18 Thread Pei Chen
Bob, If you are building from source via Eclipse, you are correct, maven should resolve those dependencies automatically for you. (Perhaps try removing any existing artifacts in your ~.m2 folder and try run-as maven generate-sources again on the project again? However, in theory, one can just add

Apache cTAKES 3.2 Release?

2014-03-26 Thread Pei Chen
Hi, I think there are a lot of items slated for the next release, I suggest we make it 3.2 instead of another patch release. I can volunteer to be the RM unless someone would like to take that up... Main Changes pending for 3.2: CTAKES-197Upgrade cTAKES to Java 7 CTAKES-292In

Re: cTakes drug ner problems..

2014-03-27 Thread Pei Chen
[Moved to dev@ list as these seem to be more developer centric] Hi, > I have so many clarifications to be solved. Can I post them frequently ? How often can I ask questions on the average ? Feel free to post to the mailing lists- just keep in mind that ASF is an all volunteer organization. See http

CTAKES-197 Upgrade cTAKES to Java 7

2014-03-31 Thread Pei Chen
FYI This has been made in trunk. There was already a discussion regarding EOL of Java 6, etc since last year [1]. Making the change to 7 in trunk for the upcoming release. [1] http://mail-archives.apache.org/mod_mbox/ctakes-dev/201306.mbox/%3CCDD26E0F.1B239%25mcoarr%40mitre.org%3E --Pei

Apache cTAKES Example Application?

2014-04-16 Thread Pei Chen
We spent some time in the past to make it easier for users to launch the CVD/CPE. But based on the questions/discussions, I think we are passed this stage and a very common use case would be for developers to use cTAKES as a lib, extend a class or two and then, embed it into their existing app. I

Blog on the recent ASF Email Outage

2014-05-28 Thread Pei Chen
Just an FYI https://blogs.apache.org/infra/entry/mail_outage_post_mortem

Additional ctakes-resources available

2014-05-28 Thread Pei Chen
In anticipation for the upcoming release, there are new cTAKES umls resources available from maven central now: The existing Lucene rxnorm_index and orangebook has been made available as a hsqldb table(s) as well. Benefits: - You can read the hsqldb directly from a jar as a stream and download the

ClearTK 2.0 upgrade

2014-06-02 Thread Pei Chen
Steve and Co., Do you know if the ClearTK 2.0 upgrade will require retraining of all of the models? --Pei

Re: query

2014-06-11 Thread Pei Chen
Harpreet, Ensure that you have downloaded the dictionaries (umls) per download page: http://ctakes.apache.org/downloads.cgi Resources Resources are required to run most of cTAKES. They are available for download from SourceForge: ctakes-resources-3.1.0.zip

Applying standard ASF headers to ytex src files

2014-06-16 Thread Pei Chen
VJ, Just an fyi, I just ran the script to apply the standard ASF license header files to the ytex source files (.sql, .xml, .java, .jsp, .bat, etc.) in trunk This will allow us to pass the Apache RAT checks... (For those who are curious, our mvn license:check and license:format will do it automat

Re: query

2014-06-17 Thread Pei Chen
trying to run it from Eclipse IDE? > > > > If so, just ensure that the resources do exist in the classpath. > > > > If it's within eclipse ide, the plugin should download and unpack the > > > > umls dictionaries automatically actually. (you can check the below

Re: query

2014-06-18 Thread Pei Chen
ect.. > > >> resources > > >> launch > > > UIMA_CVD---clinical_documents_pipeline.launch. > > > > > > I am using ctakes 3.1.1 and resouces also 3.1 > > > > > > I used this link for svn : > https://svn.apache.org/repos/asf/ctakes/t

Re: query

2014-06-18 Thread Pei Chen
llo Pei, > > > > Thank you so much for helping. > > > > > > Harpreet > > > > > > On Wed, Jun 18, 2014 at 11:08 AM, Pei Chen wrote: > > > >> Harpreet, > >> I just did a fresh checkout of trunk and could recreate the error. I > >>

Re: query

2014-06-19 Thread Pei Chen
know. > > Thank you, > Harpreet > > > > On Wed, Jun 18, 2014 at 8:02 PM, Pei Chen wrote: > > > Harpreet, > > looks like resources just made it to the maven central mirrors. But I > > didn't not get a chance to try it out or fully test it yet.

upcoming ctakes-temporal bundled models

2014-06-24 Thread Pei Chen
Does anyone happen to have a quick/simple README about the current best performing models that is being included? BackwardsTime Event DocTimeRel ContextualModality

[VOTE] Release Apache cTAKES 3.2.0

2014-06-27 Thread Pei Chen
Hi all, This is a call for a vote on releasing the following candidate (rc1) as Apache cTAKES 3.2.0. The major changes include: - New optional YTEX component(s) (Yale Extensions to cTAKES) - New optional improved/faster dictionary lookup (dictionary-lookup-fast) - New optional Temporal component (

Re: Confluence

2014-06-29 Thread Pei Chen
jtgreen has been added to the confluence wiki. --Pei On Sun, Jun 29, 2014 at 2:03 PM, John Green wrote: > Pei - Im finally getting around to working with ytex. There are some > things Id like to clarify in the install for beginners like me. How do I > edit the confluence wiki? > > JG > > Sent f

Re: Bacterium Dictionary

2014-06-30 Thread Pei Chen
Nick, I am not sure how complete it is, but I believe the UMLS has the semantic type of Bacterium [T007] It's most likely not included in the default cTAKES dictionaries though... Thanks, Pei On Mon, Jun 30, 2014 at 10:31

Re: [VOTE] Release Apache cTAKES 3.2.0

2014-07-07 Thread Pei Chen
June 30, 2014 10:24 PM > To: dev@ctakes.apache.org > Subject: RE: [VOTE] Release Apache cTAKES 3.2.0 > > This is pretty obvious, but since this is a record of what was voted upon, > note that some of the URLs contain an extra > > ctakes-3.2.0/ > > For example > > http://people.apache.org/~chenpei/RCs/ctakes-

Re: [VOTE] Release Apache cTAKES 3.2.0

2014-07-08 Thread Pei Chen
he subversion checkout > step? > > Tim > > ________ > From: Pei Chen [chen...@apache.org] > Sent: Monday, July 07, 2014 12:06 PM > To: dev@ctakes.apache.org > Subject: Re: [VOTE] Release Apache cTAKES 3.2.0 > > Thanks for testing this

Re: Retrieving CUIs

2014-07-08 Thread Pei Chen
Nick, It is fairly easy to extend an annotator (either a java class or groovy script) to extract just the items for your specific use case. Check out the HelloWorldAnnotator and Pipeline from ctakes-examples project. I can write an example that just outputs the CUI if you like, but I have a hunch

Re: Retrieving CUIs

2014-07-08 Thread Pei Chen
n Tue, Jul 8, 2014 at 3:44 PM, Nick Nikandish < snika...@emerginghealthit.com> wrote: > Hi Chen, > > I only need CUI. I tried to extend DictoanryLoopkupAnnotator. Is this a > writer approach? > > Thanks, > Nick > > -Original Message- > From: Pei Chen [m

[CANCELLED] [VOTE] Release Apache cTAKES 3.2.0

2014-07-08 Thread Pei Chen
Cancelling the rc-1. Will send out another vote thread for RC2 shortly. --Pei On Tue, Jul 8, 2014 at 10:53 AM, Pei Chen wrote: > It's the latter: > the -src is basically the same as the dev install w/o the subversion > checkout step... > > > On Tue, Jul 8, 2014 at 7

[VOTE] Release Apache cTAKES 3.2.0 (rc2)

2014-07-08 Thread Pei Chen
Hi all, The main difference between rc1 and rc2 is that we removed the lvg-res and assertion-res.jar from the distro. They still need to be unpacked. This is a call for a vote on releasing the following candidate (rc2) as Apache cTAKES 3.2.0. The major changes include: - New optional YTEX compon

[ANNOUNCE] Apache cTAKES 3.2.0 released

2014-07-23 Thread Pei Chen
The Apache cTAKES team is pleased to announce the availability of the 3.2.0 release. For the complete release notes, please visit http://s.apache.org/ctakes-3.2.0-release-notes Apache clinical Text Analysis and Knowledge Extraction System (cTAKES) is an open-source natural language processing s

cTAKES min requirements

2014-08-25 Thread Pei Chen
Since we default the runtime java heap sizes to 3g in 3.2.0, should we update our documentation to officially only support 64bit? I can only see models/pipelines being loaded into mem grow in size. I know it may seem trivial, but I still know a few unfortunate souls still on 32 bit systems… any o

org.apache.ctakes.ytex.umls.dao.UMLSDaoTest

2014-08-25 Thread Pei Chen
Hi VJ, While on the subject of unit tests- I didn't get a chance to dig deeper and was hoping you would know the cause of this unit test failure: > mvn clean install 2014-08-25 13:33:50,830 WARN net.sf.ehcache.CacheManager - Creating a new instance of CacheManager using the diskStorePath "/var/

Re: Microsoft - MSDN - Is the support continuing for ASF committers?

2014-08-25 Thread Pei Chen
Just an fyi - link for MSDN subscription license(s) for committers http://mail-archives.apache.org/mod_mbox/www-community/201305.mbox/%3c518b85e7.7000...@lehmi.de%3E https://svn.apache.org/repos/private/committers/donated-licenses/msdn-subscription.html

Re: managing ctakes resources on classpath

2014-08-26 Thread Pei Chen
I'm not too privy to the ytex config details, but yes you're right, it's caused by the xdl.xsd being null. However it looks like it exists in ytex-res.jar but the call being made uses Class.getResource which won't be able to read in from the jar as an InputStream. 1) We can make ytex read in resou

Re: MedicationMention and new Mention

2014-09-03 Thread Pei Chen
Harpreet, MedicationMention attributes such as .medicationfrequency .medicationDosage Can be filled via the DrugMentionAnnotator [1]. If I recall correctly, I believe you can just add that annotator after the DictionaryLookup in your pipeline. [1] http://svn.apache.org/repos/asf/ctakes/trunk/cta

Re: MedicationMention and new Mention

2014-09-04 Thread Pei Chen
changes in the whole ctakes hierarchy to add the > typeId for new mention. > Or just by creating a new annotator I would be able to solve this problem? > > Thanks a lot. > > Regards, > Harpreet > > > > On Wed, Sep 3, 2014 at 4:06 PM, Pei Chen w

Re: Permutations

2014-09-05 Thread Pei Chen
Hi Kim, Thanks for pointing that out. https://issues.apache.org/jira/browse/CTAKES-310 has been opened for this. If you commit the changes, we can see if we can include in the 3.2.1 patch release. I was looking at the changelist for this file, and it may look like some of these optimizations may ha

Re: Build failed in Jenkins: ctakes-trunk-package #257

2014-09-08 Thread Pei Chen
Hi Kim, Jenkins occasionally get's timeouts when trying to upload artifacts to the nightly snapshots. I just kicked it off manually, and all seems okay. On Mon, Sep 8, 2014 at 12:56 PM, Kim Ebert wrote: > Is there anything we need to do to get the build back to normal? > > Return code is: 503 , R

Re: v_document_cui_sent not being populated

2014-09-08 Thread Pei Chen
Hi Tim, Thanks for catching that- yes, would you mind creating a jira for that? Even better if you can attach a patch for it (perhaps a good idea to search/replace on the entire project) and we can include in the next 3.2.1 patch... --Pei On Mon, Sep 8, 2014 at 4:50 PM, Tim O'Connell wrote: > Hi

Re: Ctakes to process 5000K recoreds

2014-09-09 Thread Pei Chen
Nick, When you mean no medication is being annotated, I presume you mean the medication attributes (i.e. dosage, frequency, etc.) are not being annotated? I think the DrugNER needs a list of section names in the config; I think it includes SIMPLE_SEGMENT. I am very surprised that SimpleSegementAn

[DISCUSS] Apache cTAKES API

2014-09-17 Thread Pei Chen
There seems to be an increasing amount questions regarding how to 'use/integrate' cTAKES. Some folks have been discussing an effort/focus in creating a clean starting point for cTAKES. This could be in the form of a clean, well-document API. (abstracting out UIMA, Annotators, Pipelines, Type Syste

[DISCUSS] cTAKES BigTop/Hadoop integration

2014-09-22 Thread Pei Chen
Jay proposed an interesting idea of creating an app that takes in different streams of datasources, process text with cTAKES under the BigTop/Hadoop ecosystem... Initial thoughts were to have a hackathon, have something for Dec 2014, and a joint demo/effort at the next ApacheCon (04/2015). https:

Boston cTAKES Meetup

2014-09-22 Thread Pei Chen
Please feel free to join the Boston Meet up group: Upcoming Free Event: http://www.meetup.com/cTAKES/events/208836282/ (If possible, please feel free to RSVP so we can get an approx headcount) Feel free to chime in if you have anything specific that may be of interest to you: ex: cTAKES intro, cT

Re: Boston cTAKES Meetup

2014-09-22 Thread Pei Chen
end (I'm in > Vancouver)? > > Best, > Tim > > On Mon, Sep 22, 2014 at 2:40 PM, John Green > wrote: > >> Will this be recorded? >> — >> Sent from Mailbox <https://www.dropbox.com/mailbox> >> >> >> On Mon, Sep 22, 2014 at 4:30 P

Re: Boston cTAKES Meetup

2014-09-23 Thread Pei Chen
wish > I > > would be there, but it is very hard tor is not possible for me to be > there. > > > > Prakash Poudyal > > Portugal > > > > On Tue, Sep 23, 2014 at 3:31 AM, Tim O'Connell > > wrote: > > > >> thanks Pei. > >

Apache cTAKES 3.2.1 release preperation

2014-09-26 Thread Pei Chen
There is a 3.2.1 release slated for end of Oct. The major changes are: uimafit 2.1 upgrade, cleakTK upgrade, New temporal relations models. Below is a summary of what was scheduled to go in (some may be still unresolved). Feel free to edit/update Jira if you believe something should be included/om

Next cTAKES release 3.2.1 - Creating a Release Candidate

2014-10-23 Thread Pei Chen
There are a lot of good fixes and new enhancements in currently trunk. - Includes new Temporal Relations models (ex: Event relationships are available now- previously- only Event/Time entities discovery models were included.) -Plus a ton of bug fixes tracked in Jira I can volunteer to be RM again

upcoming cTAKES meetup - Boston...

2014-10-23 Thread Pei Chen
Next Friday (halloween) - feel free to drop by if you're in the area! Lunch/drinks provided..Please RSVP via http://www.meetup.com/cTAKES/events/208836282/ --Pei

Re: CTakes on github.

2014-10-30 Thread Pei Chen
Sounds good. Jay, Barring any objections from the group, would you mind opening a Jira with INFRA to set that up (read only git mirror) for cTAKES? --Pei On Thu, Oct 30, 2014 at 12:40 PM, jay vyas wrote: > Hi Pei : I Agree with (A) - the hybrid approach, so anyone can use both, or > and git.apa

Re: Chest pain absent. - polarity

2014-11-15 Thread Pei Chen
Petr, Which version of cTAKES are you using? < 3.2.0 or latest 3.2.1-rc1/trunk? Both default to use a Machine Learning based polarity algorithm. If it is missed, more training examples is probably the way to go. The latest one uses clearTK and trained with different features and training data so I

Re: UMLS validation url

2014-11-24 Thread Pei Chen
https://uts-ws.nlm.nih.gov/restful/isValidctakes.umlsuser>UMLSUser will do the trick. Pei Chen Wired Informatics <http://www.wiredinformatics.com> 265 Franklin St Ste 1702 Boston, MA 02110 tel: (617) 433-7544 pei.c...@wiredinformatics.com On Mon, Nov 24, 2014 at 3:12

[VOTE] Release Apache cTAKES 3.2.1 (rc2)

2014-12-01 Thread Pei Chen
This is a call for a vote on releasing the following candidate (rc2) as Apache cTAKES 3.2.1. The major changes include: - New optional Temporal component (Time + Event Relationships models now available) - Other bug fixes/enhancements from Jira I manually downloaded the bin as well as resources

[RESULT] [VOTE] Release Apache cTAKES 3.2.1 (rc2)

2014-12-09 Thread Pei Chen
More than 72 hours has passed. The vote for Apache cTAKES 3.2.1 (rc2) *passes* [1] with 3 +1 votes (3 binding) +1 (binding) Pei Chen Vijay Garla Tim Miller There were no -1 or +0 votes cast. I will be publishing the release, then will announce the release as soon as artifacts will be

[ANNOUNCE] Apache cTAKES 3.2.1 released

2014-12-11 Thread Pei Chen
The Apache cTAKES team is pleased to announce the availability of the 3.2.1 release. For the complete release notes, please visit http://s.apache.org/ctakes-3.2.1-release-notes Apache clinical Text Analysis and Knowledge Extraction System (cTAKES) is an open-source natural language processing sys

Re: Links Not Working

2014-12-12 Thread Pei Chen
Kasie, Thanks for point that out. Could you send us the pages with the broken links? Thanks, Pei On Fri, Dec 12, 2014 at 11:29 AM, kasie.allen wrote: > Hi! > > I came across a few links that aren't working on your website. Do you mind > telling me who I should contact about them? > > Thanks! :)

Re: Question about running cTakes, urgent!

2014-12-12 Thread Pei Chen
your patience. > > Here is the result I run the AggregatePlaintextFastUMLSProcessor.xml by > using the real medical note. But I cannot find the negation result. > > > Yu Liang > > CHIBI > > > > > > On Dec 12, 2014, at 3:59 PM, Pei Chen wrote: > > Yes, N

Re: intro video and ctakes youtube

2014-12-15 Thread Pei Chen
John, I presume you this thread: http://mail-archives.apache.org/mod_mbox/ctakes-dev/201408.mbox/%3c393252f14c42f946952f1ed75d316cad39158...@chexmbx4a.chboston.org%3E Strange, I couldn't find it anymore either... The place holder could have been auto deleted because it was empty? I think it's wor

Re: revamping the Apache cTAKES website

2014-12-15 Thread Pei Chen
che.org > > > Cc: dev@ctakes.apache.org > > > Subject: RE: revamping the Apache cTAKES website > > > > > > I would like to second the bootstrap recommendation, with the > additional > > recommendation of django for the backend. It is an amazing platform fo

Re: UMLS Integration

2014-12-16 Thread Pei Chen
://www.nlm.nih.gov/research/umls/licensedcontent/umlsknowledgesources.html The error seems to be related to incomplete or corrupted zip files? Pei Chen Wired Informatics <http://www.wiredinformatics.com> 265 Franklin St Ste 1702 Boston, MA 02110 tel: (617) 433-7544

Re: question about CTAKES

2014-12-17 Thread Pei Chen
[+dev] I think that's a current limitation in the new Polarity Classifier. It's ML based, so most likely 'Deny XYZ' or 'Negative for XYZ' is probably not in the training data. There are a couple of things I would suggest: 1) Post the questions/examples to dev@ctakes.apache.org - perhaps others ma

Re: cTakes Annotation Comparison

2014-12-19 Thread Pei Chen
ah! Excellent news... that's much more inline with our experience and evaluation results. On Fri, Dec 19, 2014 at 5:04 PM, Bruce Tietjen < bruce.tiet...@perfectsearchcorp.com> wrote: > My apologies to Sean and everyone, > > I am happy to report that I found a bug in our analysis tools that was >

Re: cTakes question

2015-01-21 Thread Pei Chen
[+dev] Yu, Yes, you can run it from the command line in many ways. 1) You can write a Java class that does it for you. Similar to http://svn.apache.org/repos/asf/ctakes/trunk/ctakes-examples/src/main/java/org/apache/ctakes/examples/pipelines/ExampleAggregatePipeline.java 2) Run the CPE (Collectio

Re: Hello cTAKES Mailing List

2015-02-23 Thread Pei Chen
Raymond, Probably a combination of UMLS *Consumer Health Vocabulary + Custom Dictionary (as Sean described) *may work for the use case*:* "OAC CHV connects informal, common words and phrases about health to technical terms used by health care professionals. It includes jargon, slang, ambiguous, and

Re: New Website

2015-02-25 Thread Pei Chen
Looks great... +1 to replace the old site! I'll take a quick double check on any ASF branding requirements at the same time. On Tue, Feb 24, 2015 at 7:29 PM, Michelle Chen wrote: > Hello everyone, > > We are planning on publishing the new website on March 2, 2015. Here is the > link to the propo

Re: cTakes setup

2015-03-13 Thread Pei Chen
Mitch, -The dev@ and user@ mailing lists are archived and searchable; it is probably the best for searching archived discussions. -Could you clarify what you are trying to achieve or the issue that you are experiencing with the -Xmx? There are models and dictionaries that get loaded into memory- i

Re: Dependency Parser model data

2015-03-15 Thread Pei Chen
Ephi, The ClearNLP models in the current cTAKES releases (since 3.1.0 [1]) should contain much more. They should contain at least MiPACQ and SHARP training data. Could you point us to the documentation so we can update it? I believe the break down was: - Clinical questions: 1,600 sentences,

Re: Ctakes Null Pointer Error for org.apache.ctakes.dependency.parser.util.DependencyUtility

2015-03-27 Thread Pei Chen
Hoang, 3.0 was released a long time ago (02/2013). (according to the tag/history, it did't have the null fix until 6/2013 3.1?) http://svn.apache.org/repos/asf/ctakes/tags/ctakes-3.0.0-incubating/ctakes-dependency-parser/src/main/java/org/apache/ctakes/dependency/parser/util/DependencyUtility.java

Re: Running cTAKES via command line

2015-04-03 Thread Pei Chen
There were a couple of recent threads about this [1]. In particular search for: CmdLineCpeRunner.java and RunCPE.java [1] http://mail-archives.apache.org/mod_mbox/ctakes-dev/201502.mbox/%3ccahnnhnzfde5mf6ddv6y2r4jyygua1a43srdnzrskjqwddti...@mail.gmail.com%3e We should probably add it to the wiki

Re: Running cTAKES via command line

2015-04-03 Thread Pei Chen
or* *org.apache.uima.examples.cpe.SimpleRunCPM (requires uima examples jar)* On Fri, Apr 3, 2015 at 11:18 AM, Pedro Teixeira wrote: > Pei Chen writes: > > > > > There were a couple of recent threads about this [1]. In particular > search > > for: > > C

Re: Getting Started with CTAKES

2015-04-08 Thread Pei Chen
stava wrote: > Thanks for the thread. I would love to meet up with CTAKES people. > > > > Please let me know how can we coordinate this. Please reach out to me my > email Id is abhishes -at- gmail -dot- com > > > > Does CTAKES have a session at apache con? &g

Re: Question about how to interpret Ctakes output

2015-04-08 Thread Pei Chen
[+dev] Yu, Check out the type system: http://svn.apache.org/repos/asf/ctakes/trunk/ctakes-type-system/src/main/resources/org/apache/ctakes/typesystem/types/TypeSystem.xml Note: I believe what you really want is *org.apache.ctakes.typesystem.type.textsem.IdentifiedAnnotation and not *org.apache.ct

cTAKES @ ApacheCon 2015 next week

2015-04-09 Thread Pei Chen
Just a reminder- Jay and I are planning to have a session (Tues) at Apache Con 2015 on using cTAKES in a Big Data context using Spark/Hadoop. If you happen to be there, feel free stop by the session. Or If you're in the neighborhood and want to meet up over coffee, feel free to drop us a note.

Re: cTakes Questions

2015-04-17 Thread Pei Chen
[+dev] Amar, 2.5 is a really outdated version of cTAKES. As for understanding the output, I think the best place to start is to take a look at: http://svn.apache.org/repos/asf/ctakes/trunk/ctakes-type-system/src/main/resources/org/apache/ctakes/typesystem/types/TypeSystem.xml Feel free to post to

Re: Small medical query parser

2015-04-17 Thread Pei Chen
Hi John, It looks pretty straightforward. Were you thinking of contributing something like this as an alternative/simplified pipeline- for those who may not want to always extract deep knowledge but just map terms to codes? Perhaps it can be even simpler if it can read the same existing bundled hs

Apache cTAKES Hackathon: Containers- Docker + Kubernetes?

2015-04-17 Thread Pei Chen
Would folks be interested in joining a hackathon nearby Boston? Exact Time and place TBA. Goal: Get cTAKES to work with Docker and Kubernetes and have a working example in sandbox. Deploying cTAKES is not so straightforward and difficult to manage, let alone in a distributed environment. Contai

Re: Include the smoking status detection in AggregatePlaintextFastUMLSProcessor.xml

2015-04-17 Thread Pei Chen
Tom, I would put it at the end of the pipeline (at a min, it should be behind sectionizer, sentence, tokenizer, lvg). I would remove ExternalBaseAggregateTAE as this simulates the sectionizer, sentence, tokenizer, lvg would would be redundant. I would also probably remove the last NegEx which cou

Re: Include the smoking status detection in AggregatePlaintextFastUMLSProcessor.xml

2015-04-21 Thread Pei Chen
gt; > > > At the top of the file, there is an import for the NegationAnnotator: > > > , but it is not > commented > > > out and never run in the fixed flow. > > > > > > Am I correct that the negation detection in the clinical pipeline is > now > > > per

Re: Request for help:: NCBO Ontology Extraction Tool for i2b2

2015-04-23 Thread Pei Chen
Sekhar, Is it happening to all of the ontologies you mentioned or just one? Those ontologies do not seem very big or deep. Did you notice in the logs if something in the ontology having some sort of circular reference or causing an infinite loop? I think lori from i2b2 may be better at answering

Re: Command-line tool for cTAKES

2015-04-30 Thread Pei Chen
If you already have the CPE running, you can pass the descriptor to the command line: *org.apache.ctakes.ytex.tools.RunCPE or * *org.apache.ctakes.core.cpe.CmdLineCpeRunner or* *org.apache.uima.examples.cpe.SimpleRunCPE http://mail-archives.apache.org/mod_mbox/ctakes-dev/201504.mbox/%3ccapqz87q

Re: Image to text conversion

2015-04-30 Thread Pei Chen
Sekhar, There are a few open Jira's: I think it would be a great contribution if you get this to work: - CTAKES-189 GSoC: Implement OCR/Tika to standardize text input for cTAKES - - CTAKES-105

[VOTE] Release Apache cTAKES 3.2.2 (rc1)

2015-05-05 Thread Pei Chen
This is a call for a vote on releasing the following candidate (rc1) as Apache cTAKES 3.2.2. The major changes include: - Improved optional Temporal models (Time + Event Relationships models now available) - Other bug fixes/enhancements from Jira (see release notes Jira link below). I manually do

Re: UMLS Authentication failing despite correct username and password

2015-05-11 Thread Pei Chen
By any chance, are you behind a firewall or proxy server? On Mon, May 11, 2015 at 6:15 PM, Tom Devel wrote: > I have the same ERROR, even when running the CVD and loading the clinical > pipeline. > > The file cTakesHsql.xml contains the lines: > > > https://uts-ws.nlm.nih.gov/restful/isValidUML

Re: UMLS Authentication failing despite correct username and password

2015-05-11 Thread Pei Chen
Michal, Thanks for pointing that out (It would have been nice if they sent out a notice about the change in the API call). Would be great if someone could open a Jira and verify this fix solves the issue... I think we should push out this critical patch asap- I can include it in 3.2.2 and create

[VOTE] Release Apache cTAKES 3.2.2 (rc2)

2015-05-13 Thread Pei Chen
This is a call for a vote on releasing the following candidate (rc2) as Apache cTAKES 3.2.2. The major change since rc1 was to include the fix for CTAKES-359 - UMLS Authentication failing despite correct username and password. For more detailed information on the changes/release notes, please vis

Re: Authentication fails for uts.nlm.nih.gov

2015-05-13 Thread Pei Chen
A release candidate that includes the UMLS Authentication fix is ready (ctakes-3.2.2-rc2) now. Please feel free to test and cast your VOTE to release it by replying to the email thread[2] [1] https://dist.apache.org/repos/dist/dev/ctakes/ctakes-3.2.2-rc2/ [2] Subject: [VOTE] Release Apache cTAKES

Re: CTAKES mirroring on github.

2015-05-18 Thread Pei Chen
One of the visions behind the *-res projects was to separate out the resources from code. In theory, one can filter out all *-res projects from their git repo and pull in any version of the resources from maven central... I won't have enough bandwidth at the moment to try it out or work on the gi

Re: fyi

2015-05-19 Thread Pei Chen
Congrats on the new role James! I hope you'll still be able to continue to contribute here. On Tue, May 19, 2015 at 9:11 PM, Masanz, James J. wrote: > > Hi all, > > Just fyi that I've been even more quiet lately than usual and that that > will continue for a while yet because I'm moving and cha

Re: [VOTE] Release Apache cTAKES 3.2.2 (rc2)

2015-05-27 Thread Pei Chen
y 18, 2015 2:59 PM > *To:* dev@ctakes.apache.org > *Subject:* Re: [VOTE] Release Apache cTAKES 3.2.2 (rc2) > > > > [ ] -1 Do not release the packages because... > > Tests run: 1, Failures: 0, Errors: 1, Skipped: 0, Time elapsed: 0.83 sec > <<< FAILURE! > > Results :

[RESULT] [VOTE] Release Apache cTAKES 3.2.2 (rc2)

2015-05-28 Thread Pei Chen
More than 72 hours has passed. The vote for Apache cTAKES 3.2.2 (rc2) *passes* [1] with 5 +1 votes (4 binding) +1 (binding) Pei Chen Tim Miller Kim Ebert Jay Vyas Michal Iglewski There were no -1 or +0 votes cast. I will be publishing the release, then will announce the release as soon as

Re: Downloads link broken

2015-05-29 Thread Pei Chen
It looks like downloads.cgi on the web site didn't have the executable svn property set in staging causing the -500 Internal Server Error. That should be fixed now. On Fri, May 29, 2015 at 3:05 PM, Tom Devel wrote: > The links on http://ctakes.apache.org/downloads are broken, too: > > User Insta

[ANNOUNCE] Apache cTAKES 3.2.2 released

2015-05-29 Thread Pei Chen
The Apache cTAKES team is pleased to announce the availability of the 3.2.2 release. For the complete release notes, please visit http://s.apache.org/ctakes-3.2.2-release-notes Apache clinical Text Analysis and Knowledge Extraction System (cTAKES) is an open-source natural language processing sys

[DRAFT] [REPORT] Apache cTAKES Jun 2015

2015-06-04 Thread Pei Chen
[DRAFT- Feel free to add/edit] --- Report from the Apache cTAKES project [Pei Chen] ## Description: Apache clinical Text Analysis and Knowledge Extraction System (cTAKES) is an open-source natural language processing system for information extraction from electronic medical

Re: [DRAFT] [REPORT] Apache cTAKES Jun 2015

2015-06-05 Thread Pei Chen
s. > I appreciate if I can get small help also. > > Thanks & Regards, > Soumya Shree > > -Original Message- > From: Pei Chen [mailto:chen...@apache.org] > Sent: Friday, June 05, 2015 2:32 AM > To: dev@ctakes.apache.org > Subject: [DRAFT] [

Re: PAD Term Spotter

2015-06-09 Thread Pei Chen
Hi Christopher, The PAD Term Spotter hasn't been supported for over a year now [1]. It was mostly written with specialized rules and no one had been maintaining it. I am not sure if there are any generic diseases annotators; if you would be willing to contribute the changes, we can incorporate it.

Apache cTAKES hosted demos and examples

2015-06-19 Thread Pei Chen
There seems to be a significant interest in having a hosted demo and examples, so I started this index page along with initial code examples: Index page: http://healthnlp.github.io/examples/ Live demo: http://52.24.118.198:8080/index.jsp --Pei

Re: Mvn package error

2015-06-23 Thread Pei Chen
Zhiwen, I think this unit test needs to be updated/fixed. Even though it runs fine in mvn compile test. In the interim- package needs to -DskipTests=true. The longer story is that once modules are packaged (i.e. lvg, dictionary) mvn loads them from the jars instead of unpacked resources. So esse

Re: How to Add the resources as a folder to the classpath? - Compilereleasefromcommandline.

2015-07-18 Thread Pei Chen
Generally, you can add the -cp in the java jvm args. I think there's probably an example in ./bin/runCVD.sh. If you're running it from the maven profile (mvn -PrunCVD compile), I don't believe that step should be necessary as it uses maven to resolve dependencies; let us know if you encounter er

Re: How to use cTakes as a UIMA component

2015-07-18 Thread Pei Chen
Ralph, Could you describe a bit on you were using the UIMA framework? i.e. PEAR files, XML descriptors, and/or uimaFIT to programmatically wire the components together? I think the easiest would be to have your application pull the necessary ctakes components from maven central and use the Annotato

Re: Resources for current Version

2015-07-19 Thread Pei Chen
Justin, There was a related thread on this topic: http://mail-archives.apache.org/mod_mbox/ctakes-dev/201507.mbox/%3c924de05c19409b438eb81de683a942d948797...@chexmbx1a.chboston.org%3e Hope that helps- -- Pei Chen Wired Informatics <http://www.wiredinformatics.com> 265 Franklin St St

Combining Knowledge- and Data-driven Methods for De-identification of Clinical Narratives

2015-07-24 Thread Pei Chen
Hi, Re: http://www.sciencedirect.com/science/article/pii/S1532046415001392 This is very interesting work and I think it would be very valuable for the general community. Is this something that you may be in interested in contributing/sharing the code with the Apache cTAKES community? Thanks, Pei

Fwd: Combining Knowledge- and Data-driven Methods for De-identification of Clinical Narratives

2015-07-30 Thread Pei Chen
[+dev] Hi Azad, This is great news! Looking forward to it. --Pei On Thu, Jul 30, 2015 at 8:16 AM, Azad Dehghan wrote: > Hi Pei, > > Just to keep you in the loop: I am currently tailoring a version of the > de-id tool for The Christie NHS Foundation Trust (UK)--this is due to be > concluded end o

Re: xml "org.apache.ctakes.core.analysis_engine.TokenizerAnnotator" not found

2015-07-30 Thread Pei Chen
Justin, Is this still an issue for you? I believe there was a known issue and someone submitted a patch: https://issues.apache.org/jira/browse/CTAKES-370?jql=component%20%3D%20ctakes-smoking-status%20AND%20project%20%3D%20CTAKES%20AND%20resolution%20%3D%20Unresolved%20ORDER%20BY%20priority%20DESC

Re: UmlsConcept subject

2015-07-30 Thread Pei Chen
Tomasz, IIRC, the code in SubjectCleartkAnalysisEngine.java should have the feature extractors used- I believe there is an ENUM of a preset of features, but do not recall exactly which one was the best performing for test set- probably best to check the source code. I think adding the plain senten

Re: Role of white-box logic/models in cTAKES

2015-08-05 Thread Pei Chen
Peter, Good to hear from you again! Yes, I believe there are some regex and rules based annotators that are in used (and probably the future for as long as it out performs other methods for certain tasks.) I don't think there is specific position form the community on this approach. (ASF's 'Do-acr

  1   2   3   >