Human-grounded Evaluations of Explanation Methods for Text Classification

Piyawat Lertvittayakumjorn, Francesca Toni


Abstract
Due to the black-box nature of deep learning models, methods for explaining the models’ results are crucial to gain trust from humans and support collaboration between AIs and humans. In this paper, we consider several model-agnostic and model-specific explanation methods for CNNs for text classification and conduct three human-grounded evaluations, focusing on different purposes of explanations: (1) revealing model behavior, (2) justifying model predictions, and (3) helping humans investigate uncertain predictions. The results highlight dissimilar qualities of the various explanation methods we consider and show the degree to which these methods could serve for each purpose.
Anthology ID:
D19-1523
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5195–5205
Language:
URL:
https://www.aclweb.org/anthology/D19-1523
DOI:
10.18653/v1/D19-1523
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D19-1523.pdf
Attachment:
 D19-1523.Attachment.zip