You are viewing a plain text version of this content. The canonical link for it is here.
Posted to users@opennlp.apache.org by HoangDuc Lai <na...@gmail.com> on 2013/09/05 11:36:52 UTC

Format of File Train for GISModel

Hi!

I'm learning about maximum entropy algorithm and trying to use opennlp
library.
But I don't know what is format of file train for this library.
I think it's format is
Feature1 Feature2 ... Featurek Label1
...
Feature1 Feature2 ... Featurek Labeln

in which Feature1->Featurek is calculated from data we have.
according to the theory of MaxEnt, each feature depends on the label.
So, I don't know how to predict, because when predict, I don't know the
label of instance which will be predicted, so cannot calculate
feature1->featurek.

Pls help me! Many thanks!


-- 
Hedspi K54 AS1
Lai Hoang Duc (ライ・ホアン・ドゥック)
Email: nangthuytinhsora@gmail.com