A Survey of the State of Explainable AI for Natural Language Processing

TL;DR

This survey reviews the current state of Explainable AI in NLP, discussing explanation types, techniques, visualization methods, and future research directions to improve interpretability of NLP models.

Contribution

It provides a comprehensive overview of explainability techniques in NLP, categorizes explanation methods, and highlights gaps and future directions in the field.

Findings

Overview of explanation categories and techniques

Analysis of current explainability methods in NLP

Identification of gaps and future research directions

Abstract

Recent years have seen important advances in the quality of state-of-the-art models, but this has come at the expense of models becoming less interpretable. This survey presents an overview of the current state of Explainable AI (XAI), considered within the domain of Natural Language Processing (NLP). We discuss the main categorization of explanations, as well as the various ways explanations can be arrived at and visualized. We detail the operations and explainability techniques currently available for generating explanations for NLP model predictions, to serve as a resource for model developers in the community. Finally, we point out the current gaps and encourage directions for future work in this important research area.