A Diagnostic Study of Explainability Techniques for Text Classification

Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma, Isabelle Augenstein


Abstract
Recent developments in machine learning have introduced models that approach human performance at the cost of increased architectural complexity. Efforts to make the rationales behind the models’ predictions transparent have inspired an abundance of new explainability techniques. Provided with an already trained model, they compute saliency scores for the words of an input instance. However, there exists no definitive guide on (i) how to choose such a technique given a particular application task and model architecture, and (ii) the benefits and drawbacks of using each such technique. In this paper, we develop a comprehensive list of diagnostic properties for evaluating existing explainability techniques. We then employ the proposed list to compare a set of diverse explainability techniques on downstream text classification tasks and neural network architectures. We also compare the saliency scores assigned by the explainability techniques with human annotations of salient input regions to find relations between a model’s performance and the agreement of its rationales with human ones. Overall, we find that the gradient-based explanations perform best across tasks and model architectures, and we present further insights into the properties of the reviewed explainability techniques.
Anthology ID:
2020.emnlp-main.263
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3256–3274
Language:
URL:
https://aclanthology.org/2020.emnlp-main.263
DOI:
10.18653/v1/2020.emnlp-main.263
Bibkey:
Cite (ACL):
Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma, and Isabelle Augenstein. 2020. A Diagnostic Study of Explainability Techniques for Text Classification. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3256–3274, Online. Association for Computational Linguistics.
Cite (Informal):
A Diagnostic Study of Explainability Techniques for Text Classification (Atanasova et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.263.pdf
Video:
 https://slideslive.com/38938813
Code
 copenlu/xai-benchmark
Data
e-SNLI