Improve Interpretability of Neural Networks via Sparse Contrastive Coding

Improve Interpretability of Neural Networks via Sparse Contrastive Coding Junhong Liu author Yijie Lin author Liang Jiang author Jia Liu author Zujie Wen author Xi Peng author 2022-12 text Findings of the Association for Computational Linguistics: EMNLP 2022 Yoav Goldberg editor Zornitsa Kozareva editor Yue Zhang editor Association for Computational Linguistics Abu Dhabi, United Arab Emirates conference publication liu-etal-2022-improve 10.18653/v1/2022.findings-emnlp.32 https://aclanthology.org/2022.findings-emnlp.32/ 2022-12 460 470