Re: Preparing for an Apache cTAKES 3.2 Release?

gt; > > > --Pei > > > > > > > >> -Original Message- > > > >> From: britt fitch [mailto:britt.fi...@gmail.com] > > > >> Sent: Monday, June 09, 2014 5:42 PM > > > >> To: dev@ctakes.apache.org > > > >

Re: sentence detector model

tence detector newline issue, > training a > >>> model to probabilistically split sentences on newlines rather than > forcing > >>> sentence breaks. I have checked in a model to the repo under > >>> ctakes-core-res. I also attached a patch to ctakes-core to

Re: [DISCUSS] new cTAKES web site

Thanks so much for your work on these! I like 1 and 4 best, pretty much for the same reasons as everyone else. Hope you all had a great holiday season! ᐧ -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Delega

Re: New cTAKES website

I'm not really familiar with the other models that exist. ᐧ -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Delegation to the House of Delegates of the American Medical Association ksa...@ksarma.com gchat: k

Re: [DISCUSS] Where should cTAKES models live?

I like b as well -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Delegation to the House of Delegates of the American Medical Association ksa...@ksarma.com gchat: ksa...@gmail.com linkedin: www.linkedin.co

Re: roadmap for Apache cTakes "big data" processing

AS compatibility is a good idea, but I suspect there will be a fair number of problems to solve on the way. I do think it is certainly doable, though. On Saturday, April 27, 2013, Andy McMurry wrote: > I'm writing to gauge community interest and intent for parallel processing > with cTakes. > > A

Re: files vs strings in collection reader

be faster than individual initialization. -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Delegation to the House of Delegates of the American Medical Association ksa...@ksarma.com gchat: ksa...@gmail.com linkedin:

Re: files vs strings in collection reader

Presumably some sort of system call is required to list the files in the directory -- there presumably is slight overhead in storing those once and then calling the file initializer on stored filenames. That being said, I agree that the overhead there is likely minuscule. -- Karthik Sarma

Re: best practices

+1 -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Delegation to the House of Delegates of the American Medical Association ksa...@ksarma.com gchat: ksa...@gmail.com linkedin: www.linkedin.com/in/ksarma On

Re: apostrophe and sentence detector

Hmm, one problem there is that medical records tend to be punctuated completely differently from normal text in my experience. -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Delegation to the House of Deleg

Re: apostrophe and sentence detector

ns. Probably a pie in the sky, though ;) Karthik -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Delegation to the House of Delegates of the American Medical Association ksa...@ksarma.com gchat: ksa...@gmail.c

Re: apostrophe and sentence detector

Hah, indeed -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Delegation to the House of Delegates of the American Medical Association ksa...@ksarma.com gchat: ksa...@gmail.com linkedin: www.linkedin.com/in/ks

Re: [ANNOUNCE] Welcome John Green as new cTAKES committer and PMC member

Welcome! Good to have another medical student around :) -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Delegation to the House of Delegates of the American Medical Association ksa...@ksarma.com gchat:

Re: RTF Annotator?

I think such a tool would be quite useful -- I imagine that David isn't the only person who works with RTF docs, and avoiding conversion should help us glean additional information as James suggests. Let me know if you need my assistance with anything! -- Karthik Sarma UCLA Medical Scie

Re: [RESULT] [VOTE] Release Apache cTAKES 3.1 (rc3)

Has there been any movement on these issues? Just took a look at the site and it looks like 3.1 isn't up yet, but haven't really been following this thread... -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics

Re: [RESULT] [VOTE] Release Apache cTAKES 3.1 (rc3)

Hmm, is resources-3.1.0 really supposed to be half the size of resources-3.0.1? -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Delegation to the House of Delegates of the American Medical Association

Re: [RESULT] [VOTE] Release Apache cTAKES 3.1 (rc3)

Good to hear! -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Delegation to the House of Delegates of the American Medical Association ksa...@ksarma.com gchat: ksa...@gmail.com linkedin: www.linkedin.co

Re: configuring cTakes for getting input from a db table and persisting output to i2b2 and/or flat db table

or my workflows. -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Delegation to the House of Delegates of the American Medical Association ksa...@ksarma.com gchat: ksa...@gmail.com linkedin: www.linkedin.com/in/ksar

Re: Apache cTAKES > cTAKES 3.1 User Install Guide

S has some non-English language dictionaries, but I suspect that some of the components wouldn't internationalize very well in some cases (i.e. RTL languages in general, LVG, smoking status, maybe the POS tagger, maybe even the tokenizer, etc). -- Karthik Sarma UCLA Medical Scientist Traini

Re: Common Type System across systems?

ystems closely and make a > > >proposal > > >(2) Agree on the proposal. > > >(3) Spend the time to re-write all the code to use the new type system. > > > > > >Step (3) is especially time consuming, but in fact, we never managed > > >to get the

Re: CTAKES-248- include original covered text of NEs which can't be recovered post if NE is from a disjoint span

Hmm, couldn't you just fetch the matched atom and use that? Should be the same information (without, I suppose, the original ordering and split). -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Dele

Re: move ytex annotators to ctakes.apache.org?

This would be quite valuable -- in particular, ytex's annotation database connection is much easier to use than what ships with cTAKES. There are a fair number of other advantages, and I think they'd all be very valuable! -- Karthik Sarma UCLA Medical Scientist Training Program C

Re: [VOTE] Release Apache cTAKES 3.1.1

+1 -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Delegation to the House of Delegates of the American Medical Association ksa...@ksarma.com gchat: ksa...@gmail.com linkedin: www.linkedin.com/in/ksarma On

Re: sentence detector newline behavior

We could possibly add some additional datasets for training. MIMIC data does come to mind -- I can't remember off the top of my head if the MIMIC dataset has sentences spanning lines or not. -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Im

Re: Clojure, having its origins in LISP, is a better fit for serious NLP work

ything special about LISP > that makes it better for NLP than other functional languages. > > Steve > -- -- Karthik Sarma UCLA Medical Scientist Training Program Class of 20?? Member, UCLA Medical Imaging & Informatics Lab Member, CA Delegation to the House of Delegates of the Ame

Re: Clojure, having its origins in LISP, is a better fit for serious NLP work

;m > >> against Clojure or that I'm recommending Groovy. But there's nothing > >> inherent about LISP that makes it a better fit for NLP. > >> > >> If you want to argue that functional paradigms (e.g. LISP, Haskell, > >> Scala, Map-Reduce) are better