+1 to do that.
We will name it MAXENT_QN_EXPERIMENTAL until
the current problems are solved.
Do you want to update the patch file to your latest version
or should we commit the latest patch file attached to the issue?
Jörn
On 09/12/2012 04:05 PM, Hyosup Shim wrote:
Hi,
It's fine that pulling it in as an experimental feature.
I think that it will be helpful that pulling it it, because following work
will be
more managable when the code is tracked by subversion.
Thanks.
2012/9/12 Jörn Kottmann <kottm...@gmail.com>
Hello,
should we pull in the patch and mark it as experimental?
Any opinions about that?
Thanks,
Jörn
On 08/26/2012 06:43 AM, Hyosup Shim wrote:
Hi,
I've been working on implmenting QNTrainer(L-bfgs maxent parameter
estimator) in recent few weeks.
My first implementation on the issue gave me about 0.80 precision on
train/test set of PerceptronPrepAttach unit test.
Since other existing estimators in OpenNLP showed nearly same precision on
that test set, I did submitted the patch.
But on CONLL02 test set Jorn gave me, QNTrainer got dissappointing result.
(less than 0.05 in precision, 0.30 in recall)
I tried to fix it, and failed. Could anyone give me a clue?
OPENNLP-338
<https://issues.apache.org/**jira/browse/OPENNLP-338<https://issues.apache.org/jira/browse/OPENNLP-338>
