Explainable Natural Language Processing
Seiten
2021
Morgan & Claypool Publishers (Verlag)
978-1-63639-213-4 (ISBN)
Morgan & Claypool Publishers (Verlag)
978-1-63639-213-4 (ISBN)
- Lieferbar
- Versandkostenfrei
- Auch auf Rechnung
- Artikel merken
Presents a taxonomy framework and survey of methods relevant to explaining the decisions and analysing 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.
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.
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.
Introduction
A Framework for Explainable NLP
Local-Backward Explanations
Global-Backward Explanations
Local-Forward Explanations of Intermediate Representations
Global-Forward Explanations of Intermediate Representations
Local-Forward Explanations of Continuous Output
Global-Forward Explanations of Continuous Output
Local-Forward Explanations of Discrete Output
Global-Forward Explanations of Discrete Output Evaluating Explanations
Perspectives
Resources
Bibliography
Author's Biography
Erscheinungsdatum | 28.09.2021 |
---|---|
Reihe/Serie | Synthesis Lectures on Human Language Technologies |
Verlagsort | San Rafael |
Sprache | englisch |
Maße | 191 x 235 mm |
Themenwelt | Mathematik / Informatik ► Mathematik ► Algebra |
Mathematik / Informatik ► Mathematik ► Angewandte Mathematik | |
Technik ► Maschinenbau | |
ISBN-10 | 1-63639-213-X / 163639213X |
ISBN-13 | 978-1-63639-213-4 / 9781636392134 |
Zustand | Neuware |
Haben Sie eine Frage zum Produkt? |
Mehr entdecken
aus dem Bereich
aus dem Bereich
Buch | Softcover (2022)
Springer Spektrum (Verlag)
CHF 55,95