Is there a generally accepted procedure for identifying why an annotation
wasnt made?
JG
Do you mean something like figuring out why a named entity wasn't
detected or something? I don't think we have anything formalized, but my
technique is something like, find the smallest text example that
demonstrates the issue and then work backwards in the pipeline. So for
something missed by the
Sounds like a good starting place to me, thanks Tim.—
Sent from Mailbox for iPhone
On Wed, Jul 16, 2014 at 3:06 PM, Miller, Timothy
wrote:
> Do you mean something like figuring out why a named entity wasn't
> detected or something? I don't think we have anything formalized, but my
> technique is
It depends on the type of annotation.
Some are rule-based. Some are machine-learning based (models). Some are
dictionary dependent. And some are based on annotations earlier in the
pipeline, and so looking at the part of speech tags within the tokens, for
example, can explain which chunk som
FYI, so far I have done the following steps:
downloaded the source archive
compiled it using: maven compile
downloaded the separately available resources
set up classpath to include e.g. jars (from the bin distribution)
set ctakes.umlsuser and ctakes.umlspw env vars
run runctakesCVD.bat
loaded
