A Survey of the State of Explainable AI for Natural Language Processing
174 Citations•2020•
Marina Danilevsky, Kun Qian, Ranit Aharonov
journal unavailable
The operations and explainability techniques currently available for generating explanations for NLP model predictions are detailed to serve as a resource for model developers in the community and to point out the current gaps.
Abstract
Marina Danilevsky, Kun Qian, Ranit Aharonov, Yannis Katsis, Ban Kawas, Prithviraj Sen. Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing. 2020.