Towards making NLG a voice for interpretable Machine Learning

James Forrest, Somayajulu Sripada, Wei Pang, George Coghill


Abstract
This paper presents a study to understand the issues related to using NLG to humanise explanations from a popular interpretable machine learning framework called LIME. Our study shows that self-reported rating of NLG explanation was higher than that for a non-NLG explanation. However, when tested for comprehension, the results were not as clear-cut showing the need for performing more studies to uncover the factors responsible for high-quality NLG explanations.
Anthology ID:
W18-6522
Volume:
Proceedings of the 11th International Conference on Natural Language Generation
Month:
November
Year:
2018
Address:
Tilburg University, The Netherlands
Editors:
Emiel Krahmer, Albert Gatt, Martijn Goudbeek
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
177–182
Language:
URL:
https://aclanthology.org/W18-6522
DOI:
10.18653/v1/W18-6522
Bibkey:
Cite (ACL):
James Forrest, Somayajulu Sripada, Wei Pang, and George Coghill. 2018. Towards making NLG a voice for interpretable Machine Learning. In Proceedings of the 11th International Conference on Natural Language Generation, pages 177–182, Tilburg University, The Netherlands. Association for Computational Linguistics.
Cite (Informal):
Towards making NLG a voice for interpretable Machine Learning (Forrest et al., INLG 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/W18-6522.pdf