A causal framework for explaining the predictions of black-box sequence-to-sequence models

David Alvarez-Melis, Tommi S. Jaakkola. A causal framework for explaining the predictions of black-box sequence-to-sequence models. In Martha Palmer, Rebecca Hwa, Sebastian Riedel, editors, Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, September 9-11, 2017. pages 412-421, Association for Computational Linguistics, 2017. [doi]

Abstract

Abstract is missing.