hooray for Haskell NLP activity!

[Grzegorz Chrupała]

Just as an aside, parameter estimation for logistic regression using
Stochastic Gradient Descent is easier to implement than smth like
LBFGS and in practice works nice (in terms of speed and accuracy).
See e.g. http://lingpipe.files.wordpress.com/2008/04/lazysgdregression.pdf
Best,
--
'gʒɛgɔʃ



On Fri, Nov 26, 2010 at 13:37, David MacIver <david at drmaciver.com> wrote:
> On 26 November 2010 12:27, Daniël de Kok <me at danieldk.eu> wrote:
>> On Nov 26, 2010, at 10:04 AM, Eric Kow wrote:
>>> Woo! It's nice to see this list picking up.
>>>
>>> 1. It's great to see all the tools that people are releasing on hackage.
>>>   We now have 23 packages listed on
>>>    <http://hackage.haskell.org/packages/archive/pkg-list.html#cat:natural language processing>
>>
>> And there are some related packages, that are not in the NLP category. For instance, there is the lbfgs parameter estimator package, and we are working on a maximum entropy modeling package based on that. While it's not NLP-specific, its development is NLP driven.
>
> For what it's worth, I'd love to see that. I've been keeping half an
> eye out for a good maxent package that isn't in C++ or on the JVM for
> a while (I have a project currently built in JRuby on top of
> OpenNLP/maxent which I'd love to move off the JVM and would be very
> happy to move out of ruby, but every attempt I've tried has resulted
> in the prediction quality being completely rubbish)
>
> _______________________________________________
> NLP mailing list
> NLP at projects.haskell.org
> http://projects.haskell.org/cgi-bin/mailman/listinfo/nlp
>