Skip to content
/ DiSAN Public
forked from taoshen58/DiSAN

Code of Directional Self-Attention Network (DiSAN)

License

Notifications You must be signed in to change notification settings

bmaneesh/DiSAN

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Directional Self-Attention Network

Cite this paper using BibTex:

@inproceedings{shen2018disan,
Author = {Shen, Tao and Zhou, Tianyi and Long, Guodong and Jiang, Jing and Pan, Shirui and Zhang, Chengqi},
Booktitle = {AAAI Conference on Artificial Intelligence},
Title = {DISAN: Directional self-attention network for rnn/cnn-free language understanding},
Year = {2018}
}

Overall Requirements

  • Python3 (verified on 3.5.2, or Anaconda3 4.2.0)
  • tensorflow>=1.2

Python Packages:

  • numpy

This repo includes three part as follows:

  1. Directionnal Self-Attention Network independent file -> file disan.py
  2. DiSAN implementation for Stanford Natural Language Inference -> dir SNLI_disan
  3. DiSAN implementation for Stanford Sentiment Classification -> dir SST_disan

The Usage of disan.py will be introduced below, and as for the implementation of SNLI and SST, please enter corresponding folder for further introduction.

And, Code for the other experiments (e.g. SICK, MPQA, CR etc.) appeared in the paper is under preparation.


Usage of disan.py

Parameters:

  • param rep_tensor: 3D tensorflow dense float tensor [batch_size, max_len, dim]
  • param rep_mask: 2D tensorflow bool tensor as mask for rep_tensor, [batch_size, max_len]
  • param scope: tensorflow variable scope
  • param keep_prob: float, dropout keep probability
  • param is_train: tensorflow bool scalar
  • param wd: if wd>0, add related tensor to tf collectoion "weight_decay" for further l2 decay
  • param activation: disan activation function [elu|relu|selu]
  • param tensor_dict: a dict to record disan internal attention result (insignificance)
  • param name: record name suffix (insignificance)

Output:

2D tensorflow dense float tensor, which shape is [batch_size, dim] as the encoding result for each sentence.


Acknowledgements

  • Some basic neural networks are copied from Minjoon's Repo, including RNN cell, dropout-able dynamic RNN etc.

About

Code of Directional Self-Attention Network (DiSAN)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%