Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Ra1nyHouse/FNText

Folders and files

NameName
Last commit message
Last commit date

Latest commit

History

11 Commits

Repository files navigation

FNText

Introduction

FNText is a fast neural model for text classification. Please note that there are many powerful and open-source frameworks to quickly prototype deep neural networks. It is widely used (Google, Baidu) industry standard. However, most of them need to translate input data into machine-readable arrays. The input texts are padded or truncated to a fixed size. This tran translation may increase the training time or cause information loss. Thus we implement our model by C99 and OpemMP, which can receive variable-length sequence as input, rather than fixed array.

The model is shown as follows:

model

Experiment Results

results

Usage

params

  • -train training data path
  • -test testing data path
  • -vali validation data path
  • -dim dimension of word vectors
  • -vocab vocabulary size
  • -epoch epoch
  • -batch-size batch size
  • -thread number of threads
  • -limit-vocab (float) limiting vocabulary

command line

fntext -train train/data/path -test test/data/path -vali vali/data/path -dim 600 -vocab 350000 -category 2 -epoch 5 -batch-size 1000 -thread 20 -limit-vocab 1
fntext_bi -train train/data/path -test test/data/path -vali vali/data/path -dim 600 -vocab 350000 -category 2 -epoch 5 -batch-size 1000 -thread 20 -limit-vocab 1

About

A fast neural model for text classification.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

AltStyle によって変換されたページ (->オリジナル) /