Don You may want to see "semantic medline" and semrep from NLM-- in general ctakes is better for physician notes whereas metamap may be better on literature. Extracting predicate relationships-- you can even download a huge database of preprocessed papers
On Feb 27, 2018 10:43 AM, "Don Flinn" <[email protected]> wrote: > Hi Sean, > > I ran the batch file and got the following error, so I have something > basically wrong, but don't know what. Any help appreciated - Don > > My input: > bin/runClinicalPipeline -i /tmp/files/CtakesInput --xmiOut > /tmp/files/CtakesOutput --user <my userName> --pass <myPass> > > myUsername and password are correct as I have used them in a number of the > cTakes examples and they were verified. The xmiOut directory contains a > three short text files, but I don't think the script even got that far. I > don't know what the error message means or how to correct it. > > The output: > 27 Feb 2018 13:01:01 INFO SentenceDetector - Sentence detector model file: > org/apache/ctakes/core/sentdetect/sd-med-model.zip > 27 Feb 2018 13:01:01 INFO TokenizerAnnotatorPTB - Initializing > org.apache.ctakes.core.ae.TokenizerAnnotatorPTB > 27 Feb 2018 13:01:01 INFO ContextDependentTokenizerAnnotator - Finite > state machines loaded. > 27 Feb 2018 13:01:01 INFO POSTagger - POS tagger model file: > org/apache/ctakes/postagger/models/mayo-pos.zip > 27 Feb 2018 13:01:01 INFO Chunker - Chunker model file: > org/apache/ctakes/chunker/models/chunker-model.zip > 27 Feb 2018 13:01:02 INFO AbstractJCasTermAnnotator - Using dictionary > lookup window type: org.apache.ctakes.typesystem.type.textspan.Sentence > 27 Feb 2018 13:01:02 INFO AbstractJCasTermAnnotator - Exclusion tagset > loaded: CC CD DT EX IN LS MD PDT POS PP PP$ PRP PRP$ RP TO VB VBD VBG VBN > VBP VBZ WDT WP WPS WRB > 27 Feb 2018 13:01:02 INFO AbstractJCasTermAnnotator - Using minimum term > text span: 3 > 27 Feb 2018 13:01:02 INFO AbstractJCasTermAnnotator - Using Dictionary > Descriptor: org/apache/ctakes/dictionary/lookup/fast/sno_rx_16ab.xml > 27 Feb 2018 13:01:02 ERROR PiperFileRunner - Initialization of annotator > class "org.apache.ctakes.dictionary.lookup2.ae.DefaultJCasTermAnnotator" > failed. (Descriptor: <unknown>) > > > On Tue, Feb 27, 2018 at 8:21 AM, Finan, Sean < > [email protected]> wrote: > > > Hi Don, > > > > The default clinical pipeline will provide a little more information: > > > > https://cwiki.apache.org/confluence/display/CTAKES/ > > Default+Clinical+Pipeline > > > > Sean > > > > > > -----Original Message----- > > From: Don Flinn [mailto:[email protected]] > > Sent: Tuesday, February 27, 2018 4:16 AM > > To: [email protected] > > Subject: Trying to Understand cTAKES [EXTERNAL] > > > > HI, > > I'm new to cTAKES and am trying to understand the product. One of my > > goals is to read in medical research documents in a given medical domain, > > glean semantic information from them and put the information into a > > database, which I can query. I have run through the cTAKES examples and > > they seem to go as far as parts of speech (POS). Poking around I found > > ClinicalPipelineFactory.java, which computes Subject. Are there other > > examples which go further into the semantics? > > > > Thanks for any help > > Don > > >
