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

Hanjie Chen | Song Feng | Jatin Ganhotra | Hui Wan | Chulaka Gunasekara | Sachindra Joshi | Yangfeng Ji |

Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing BlackboxNLP EMNLP

Sanchit Sinha | Hanjie Chen | Arshdeep Sekhon | Yangfeng Ji | Yanjun Qi |

Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection ACL

Hanjie Chen | Guangtao Zheng | Yangfeng Ji |

evision PDF of 'Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers EMNLP

Hanjie Chen | Yangfeng Ji |