Do Human Rationales Improve Machine Explanations?

Julia Strout, Ye Zhang, Raymond Mooney


Abstract
Work on “learning with rationales” shows that humans providing explanations to a machine learning system can improve the system’s predictive accuracy. However, this work has not been connected to work in “explainable AI” which concerns machines explaining their reasoning to humans. In this work, we show that learning with rationales can also improve the quality of the machine’s explanations as evaluated by human judges. Specifically, we present experiments showing that, for CNN-based text classification, explanations generated using “supervised attention” are judged superior to explanations generated using normal unsupervised attention.
Anthology ID:
W19-4807
Volume:
Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Month:
August
Year:
2019
Address:
Florence, Italy
Editors:
Tal Linzen, Grzegorz Chrupała, Yonatan Belinkov, Dieuwke Hupkes
Venue:
BlackboxNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
56–62
Language:
URL:
https://aclanthology.org/W19-4807
DOI:
10.18653/v1/W19-4807
Bibkey:
Cite (ACL):
Julia Strout, Ye Zhang, and Raymond Mooney. 2019. Do Human Rationales Improve Machine Explanations?. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 56–62, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Do Human Rationales Improve Machine Explanations? (Strout et al., BlackboxNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/W19-4807.pdf