Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Hanjie Chen

Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing


Aug 11, 2021
Sanchit Sinha, Hanjie Chen, Arshdeep Sekhon, Yangfeng Ji, Yanjun Qi

* 8 pages, 5 appendix pages 

  Access Paper or Ask Questions

Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks


Apr 13, 2021
Hanjie Chen, Song Feng, Jatin Ganhotra, Hui Wan, Chulaka Gunasekara, Sachindra Joshi, Yangfeng Ji

* NAACL-HLT 2021 

  Access Paper or Ask Questions

Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers


Oct 01, 2020
Hanjie Chen, Yangfeng Ji

* EMNLP 2020 

  Access Paper or Ask Questions

Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection


Apr 04, 2020
Hanjie Chen, Guangtao Zheng, Yangfeng Ji

* Accepted to ACL 2020 

  Access Paper or Ask Questions

Improving the Explainability of Neural Sentiment Classifiers via Data Augmentation


Oct 09, 2019
Hanjie Chen, Yangfeng Ji

* 11 pages, NeurIPS 2019 Workshop on Robust AI in Financial Services 

  Access Paper or Ask Questions

Improving the Interpretability of Neural Sentiment Classifiers via Data Augmentation


Sep 10, 2019
Hanjie Chen, Yangfeng Ji


  Access Paper or Ask Questions