A Diagnostic Study of Explainability Techniques for Text Classification

By Pepa Atanasova, Jakob Grue Simonsen, Christina Lioma, Isabelle Augenstein. 2020

278 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Measuring Association Between Labels and Free-Text Rationales (2020, background): “Choices for f include L 1 or L 2 norm (Atanasova et al., 2020), or an element-wise sum (Wallace et al., 2019).”
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2022, background): “Ideally, an explanation is “nothing but the truth” [131], and high correctness is desired [8, 15, 25, 111, 130, 131, 207, 215, 233, 241, 282, 295].”