search

lpq29743 / RAM

A TensorFlow implementation for "Recurrent Attention Network on Memory for Aspect Sentiment Analysis"
MIT License
68 stars 21 forks source link

Visualize the attention #9

Closed saja1994 closed 5 years ago

saja1994 commented 5 years ago

Hello

Thank you for the implementation. Please, can you help me to visualize the attention weights at each hop as mentioned figures in the original paper?

Regards,

lpq29743 commented 5 years ago
  1. As mentioned in “Yequan Wang, Minlie Huang, Xiaoyan Zhu, and Li Zhao. 2016. Attention-based lstm for aspect-level sentiment classification. In EMNLP, pages 606–615.”, HEMI (Wankun Deng, Yongbo Wang, Zexian Liu, Han Cheng, and Yu Xue. 2014. Hemi: a toolkit for illustrating heatmaps. PloS one, 9(11):e111988.) was used to visualize the attention.
  2. Actually, I can't find some effective tools to visualize the attention, welcome to share your method if you find some useful tools.
saja1994 commented 5 years ago

Thank you. Yes, I have used HEMI to visualize the attention. it's a simple and straightforward program to be used.