Cancelling this VOTE and will push out another release candidate soon,
uncovered an issue with SentenceDetect wherein the default EOS is \n if a
model already doesn't have EOS chars set.




On Sun, Jul 2, 2017 at 1:13 PM, Joern Kottmann <[email protected]> wrote:

> Hello,
>
> one question, did you retrain or use existing models?
>
> Jörn
>
> On Sat, Jul 1, 2017 at 10:20 PM, Richard Eckart de Castilho
> <[email protected]> wrote:
> > Hi all,
> >
> > I ran a DKPro Core build against the RC. Looks mostly fine. No code
> changes
> > are required after switching from 1.8.0 to 1.8.1. All unit tests except
> one
> > run as before.
> >
> > I can observer a change when training a sentence splitter model.
> >
> > With 1.8.0, I get
> >
> >   F-score     0.937518
> >   Precision   0.932157
> >   Recall      0.942941
> >
> > With 1.8.1, I get
> >
> >   F-score     0.922556
> >   Precision   0.909975
> >   Recall      0.935490
> >
> > I am using the germeval-2014 data for training.
> >
> > It is not a big drop, but it still is a change - maybe an undesired one?
> >
> > Best,
> >
> > -- Richard
> >
>

Reply via email to