Explainable NLP
Summary
Preface
1
Introduction
2
Interpretability and Explainability
2.1
Definition
2.2
Importance of interpretability
2.2.1
Interpretability Goals
2.2.2
Stakeholders
2.2.3
Question Types
2.3
Taxonomy of Interpretability Methods
2.3.1
Intrinsic or Post-hoc
2.3.2
Model-specific or Model-agnostic
2.3.3
Local or Global
3
Glossary
4
Datasets
4.1
Fake News (Text Classification)
5
Local Surrogate (LIME)
5.0.1
Examples
5.0.2
Advantages
5.0.3
Disadvantages
References
R Packages Used
Published with bookdown
Jinfen
Explainable Natural Language Processing
Chapter 2
Interpretability and Explainability