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

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.

To appear in AACL-IJCNLP 2020

References in corpus (2)

• One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
• The Price of Interpretability

Cited by in corpus (32)

• Unifying Large Language Models and Knowledge Graphs: A Roadmap
• Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research
• Controllable Protein Design with Language Models
• A Survey on Explainable Artificial Intelligence for Cybersecurity
• On the Explainability of Natural Language Processing Deep Models
• A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
• Explainable Artificial Intelligence (XAI) for Malware Analysis: A Survey of Techniques, Applications, and Open Challenges
• Natural Language Interfaces to Data
• Human Interpretation of Saliency-based Explanation Over Text
• ferret: a Framework for Benchmarking Explainers on Transformers
• Exploring the Landscape of Natural Language Processing Research
• Towards consistency of rule-based explainer and black box model -- fusion of rule induction and XAI-based feature importance
• A Comprehensive Survey on Self-Interpretable Neural Networks
• NLPGuard: A Framework for Mitigating the Use of Protected Attributes by NLP Classifiers
• ExClaim: Explainable Neural Claim Verification Using Rationalization
• Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability
• Nearest neighbour approaches for Emotion Detection in Tweets
• Extractive Text Summarization Using Generalized Additive Models with Interactions for Sentence Selection
• Can BERT eat RuCoLA? Topological Data Analysis to Explain
• Survey in Characterizing Semantic Change
• Sequential Attention Module for Natural Language Processing
• Tracking Peaceful Tractors on Social Media -- XAI-enabled analysis of Red Fort Riots 2021
• The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results
• Boosting Explainability through Selective Rationalization in Pre-trained Language Models
• DAHRS: Divergence-Aware Hallucination-Remediated SRL Projection
• Measuring a Texts Fairness Dimensions Using Machine Learning Based on Social Psychological Factors
• Fine-grained Interpretation and Causation Analysis in Deep NLP Models
• LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking
• Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools
• WMDecompose: A Framework for Leveraging the Interpretable Properties of Word Mover's Distance in Sociocultural Analysis
• XPROAX-Local explanations for text classification with progressive neighborhood approximation
• Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors