Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing Sanchit Sinha author Hanjie Chen author Arshdeep Sekhon author Yangfeng Ji author Yanjun Qi author 2021-11 text Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP Jasmijn Bastings editor Yonatan Belinkov editor Emmanuel Dupoux editor Mario Giulianelli editor Dieuwke Hupkes editor Yuval Pinter editor Hassan Sajjad editor Association for Computational Linguistics Punta Cana, Dominican Republic conference publication sinha-etal-2021-perturbing 10.18653/v1/2021.blackboxnlp-1.33 https://aclanthology.org/2021.blackboxnlp-1.33/ 2021-11 420 434