incubator-ctakes-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Steven Bethard <steven.beth...@Colorado.EDU>
Subject Re: generify relation extractor annotator
Date Thu, 13 Dec 2012 15:55:41 GMT
On Dec 13, 2012, at 4:41 PM, Jörn Kottmann <kottmann@gmail.com> wrote:
> On 12/13/2012 04:08 PM, Steven Bethard wrote:
>> On Dec 13, 2012, at 4:04 PM, Jörn Kottmann <kottmann@gmail.com> wrote:
>>> 
>>> What do you think about starting a relation extractor component over at
>>> OpenNLP?
>> I suspect this is probably unlikely, given that we're already using ClearTK-style
training, feature extraction, etc. and I'm pretty sure OpenNLP doesn't want to depend on ClearTK
modules...
> The only requirement for me which is really important is that it is 
> generic and can be trained/adapted for the news domain,
> usually I try to avoid the dependency on UIMA in my NLP components 
> because it makes them hard to integrate when you
> do not want to use UIMA.

Yeah, that pretty much excludes anything ClearTK based - ClearTK is far too deeply integrated
with UIMA. At one point, we were trying to segregate the classifier code from the UIMA code,
but we gave up on that because no one was using it outside of UIMA. It might be worth revisiting
that at some point, but it would be a ton of work.

Steve



Mime
View raw message