search

attardi / deepnl

Deep Learning for Natural Language Processing
GNU General Public License v3.0
457 stars 116 forks source link

Using dev set on train #26

Closed sld closed 8 years ago

sld commented 8 years ago

Hello, thanks for the great library!

In README noted to use dev data to train model.

Is it necessary to use dev data (eng.testa + eng.train) in train stage to reproduce 89% F1?

sld commented 8 years ago

By looking to the http://arxiv.org/abs/1603.06270 I found that to reproduce 89% F1 I need only train data.