Skip to content

Latest commit

 

History

History
28 lines (15 loc) · 467 Bytes

README.md

File metadata and controls

28 lines (15 loc) · 467 Bytes

!!WARNING!!

This porject is porting our original code in Theano to Tensorflow. Still in very early stage and under heavy development.

INTRODUCTION

Implementation of Neural Language Correction (http://arxiv.org/abs/1603.09727) on Tensorflow

DEPENDENCIES

Tensorflow 0.7 or 0.8

TRAINING

To train character level model (default):

$ python nlc.py

To train word level model:

$ python nlc.py --tokenizer WORD