This book presents a taxonomy framework and survey of methods relevant to explaining the decisions and analyzing the inner workings of Natural Language Processing (NLP) models. The book is intended to provide a snapshot of Explainable NLP, though the field continues to rapidly grow. The book is intended to be both readable by first-year M.Sc. students and interesting to an expert audience. The book opens by motivating a focus on providing a consistent taxonomy, pointing out inconsistencies and redundancies in previous taxonomies. It goes on to present (i) a taxonomy or framework for thinking about how approaches to explainable NLP relate to one another; (ii) brief surveys of each of the classes in the taxonomy, with a focus on methods that are relevant for NLP; and (iii) a discussion of the inherent limitations of some classes of methods, as well as how to best evaluate them. Finally, the book closes by providing a list of resources for further research on explainability.

Anders Søgaard is a father of three and a published poet, as well as a Full Professor in Computer Science the University of Copenhagen. He is currently funded by the Novo Nordisk Foundation, the Lundbeck Foundation, and the Innovation Fund Denmark; before that, he held an ERC Starting Grant and a Google Focused Research Award. He has won best paper awards at NAACL, EACL, CoNLL, etc. He previously wrote Semi-Supervised Learning and Domain Adaptation in NLP (Morgan & Claypool, 2013) and Cross-Lingual Word Embeddings (Morgan & Claypool, 2019), the latter with co-authors Ivan Vulic, Sebastian Ruder, and Manaal Faruqui.