Skip to content

Latest commit

 

History

History
12 lines (9 loc) · 601 Bytes

README.md

File metadata and controls

12 lines (9 loc) · 601 Bytes

Tensorflow implementation of attention mechanism for text classification tasks.
Inspired by "Hierarchical Attention Networks for Document Classification", Zichao Yang et al. (http://www.aclweb.org/anthology/N16-1174).

Requirements

  • Python >= 2.6
  • Tensorflow >= 1.0
  • Keras (IMDB dataset)
  • tqdm

To view visualization example visit http://htmlpreview.github.io/?https://github.com/ilivans/tf-rnn-attention/blob/master/visualization.html

My bachelor's thesis on sentiment classification of Russian texts using Bi-RNN with attention mechanism: https://github.com/ilivans/attention-sentiment