The API only supports tokenized input. Jörn
On Mon, Dec 19, 2016 at 3:30 PM, Damiano Porta <[email protected]> wrote: > Jorn, yes you are right, my apologies. > > I am doing the senteces detection (with a custom italian model), so yes i > work with the tokens of each sentence inside my custom feature generator, > but i would like to get the original text sentence too without > tokenization. > > I am finding a way to pass the original text too and analyze it inside the > createFeatures() callback. > > Is it possible somehow? > > 2016-12-19 13:54 GMT+01:00 Joern Kottmann <[email protected]>: > > > Hello, > > > > the question is not clear to me. The feature generator sees the current > > sentence only. > > > > Jörn > > > > On Sat, Dec 17, 2016 at 1:13 AM, Damiano Porta <[email protected]> > > wrote: > > > > > Hello, > > > is it possible to get/pass the original text inside a Custom NER > Feature > > > Generator somehow? > > > > > > Thanks > > > Damiano > > > > > >
