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

A causal framework for explaining the predictions of black-box sequence-to-sequence models David Alvarez-Melis author Tommi Jaakkola author 2017-09 text Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing Martha Palmer editor Rebecca Hwa editor Sebastian Riedel editor Association for Computational Linguistics Copenhagen, Denmark conference publication alvarez-melis-jaakkola-2017-causal 10.18653/v1/D17-1042 https://aclanthology.org/D17-1042/ 2017-09 412 421