Learning to Explain: Generating Stable Explanations Fast
Xuelin
Situ
author
Ingrid
Zukerman
author
Cecile
Paris
author
Sameen
Maruf
author
Gholamreza
Haffari
author
2021-08
text
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Chengqing
Zong
editor
Fei
Xia
editor
Wenjie
Li
editor
Roberto
Navigli
editor
Association for Computational Linguistics
Online
conference publication
The importance of explaining the outcome of a machine learning model, especially a black-box model, is widely acknowledged. Recent approaches explain an outcome by identifying the contributions of input features to this outcome. In environments involving large black-box models or complex inputs, this leads to computationally demanding algorithms. Further, these algorithms often suffer from low stability, with explanations varying significantly across similar examples. In this paper, we propose a Learning to Explain (L2E) approach that learns the behaviour of an underlying explanation algorithm simultaneously from all training examples. Once the explanation algorithm is distilled into an explainer network, it can be used to explain new instances. Our experiments on three classification tasks, which compare our approach to six explanation algorithms, show that L2E is between 5 and 7.5\times10\⁴ times faster than these algorithms, while generating more stable explanations, and having comparable faithfulness to the black-box model.
situ-etal-2021-learning
10.18653/v1/2021.acl-long.415
https://aclanthology.org/2021.acl-long.415
2021-08
5340
5355