Tom
    I am refering to the document classifier, not the named entity extract

    It is very difficult to use this tool in a production environment
without these details
  IfI can't get answers to these questions, I will be forced to stop using
the tool
and return to a standard SVM

Charles



On Wed, Nov 13, 2013 at 12:37 PM, Thomas Zastrow <[email protected]>wrote:

> Dear Charles,
>
> There is no more detailed description about the NE model. The raw data
> is available on the homepage and I created the models following the
> OpenNLP documentation:
>
> http://opennlp.apache.org/documentation/1.5.3/manual/opennlp.html#tools.namefind.training
>
> Best,
>
> Tom
>
>
>
> Am 13.11.2013 18:18, schrieb Charles Martin:
> > Where I can i find a detailed description of the model.bin file and the
> > scoring functions for the document classifier?
> >
> >
> >
> >
> > On Wed, Nov 13, 2013 at 1:32 AM, Thomas Zastrow <[email protected]
> >wrote:
> >
> >> Am 12.11.2013 21:19, schrieb Jörn Kottmann:
> >>
> >>> On 11/12/2013 09:11 PM, Thomas Zastrow wrote:
> >>>
> >>>> Are there any plans to merge the repositories? Any other sources for
> >>>> models?
> >>>>
> >>>
> >>> There are a few people here and there publishing models on their sites,
> >>> we should add a model link page to our wiki, so people can easily find
> >>> them.
> >>>
> >>> Jörn
> >>>
> >> I think this is a good idea. The main point here is in my oppinion, that
> >> most models were created by using copyright protected material, which
> puts
> >> them into a grey zone. Thats the reason why many people are not
> >> distributing them.
> >>
> >> But anyway, having a list of models would be great.
> >>
> >> Best,
> >>
> >> Tom
> >>
> >> --
> >> Dr. Thomas Zastrow
> >> Riemerfeldring 7a
> >>
> >> 85748 Garching
> >> Tel.: 0162 422 8029
> >> www.thomas-zastrow.de
> >>
> >>
> >
> >
>
>


-- 
This e-mail message, and any attachments, is intended only for the use of
the individual or entity identified in the alias address of this message
and may contain information that is confidential, privileged and subject to
legal restrictions and penalties regarding its unauthorized disclosure and
use. Any unauthorized review, copying, disclosure, use or distribution is
strictly prohibited. If you have received this e-mail message in error,
please notify the sender immediately by reply e-mail and delete this
message, and any attachments, from your system. Thank you.

Reply via email to