Rationalization for Explainable NLP: A Survey

Abstract

Recent advances in deep learning have improved the performance of many Natural Language Processing (NLP) tasks such as translation, question-answering, and text classification. However, this improvement comes at the expense of model explainability. Black-box models make it difficult to understand the internals of a system and the process it takes to arrive at an output. Numerical (LIME, Shapley) and visualization (saliency heatmap) explainability techniques are helpful; however, they are insufficient because they require specialized knowledge. These factors led rationalization to emerge as a more accessible explainable technique in NLP. Rationalization justifies a model's output by providing a natural language explanation (rationale). Recent improvements in natural language generation have made rationalization an attractive technique because it is intuitive, human-comprehensible, and accessible to non-technical users. Since rationalization is a relatively new field, it is disorganized. As the first survey, rationalization literature in NLP from 2007-2022 is analyzed. This survey presents available methods, explainable evaluations, code, and datasets used across various NLP tasks that use rationalization. Further, a new subfield in Explainable AI (XAI), namely, Rational AI (RAI), is introduced to advance the current state of rationalization. A discussion on observed insights, challenges, and future directions is provided to point to promising research opportunities.

References in corpus (12)

• Sequence to Sequence Learning with Neural Networks
• Towards A Rigorous Science of Interpretable Machine Learning
• Post-hoc Interpretability for Neural NLP: A Survey
• A Survey on AI Assurance
• WT5?! Training Text-to-Text Models to Explain their Predictions
• A Survey of Deep Learning Techniques for Neural Machine Translation
• Explain and Predict, and then Predict Again
• A Game Theoretic Approach to Class-wise Selective Rationalization
• A Survey on Explainability in Machine Reading Comprehension
• Understanding Interlocking Dynamics of Cooperative Rationalization
• ExClaim: Explainable Neural Claim Verification Using Rationalization
• RerrFact: Reduced Evidence Retrieval Representations for Scientific Claim Verification

Cited by in corpus (4)

• ExClaim: Explainable Neural Claim Verification Using Rationalization
• This Reads Like That: Deep Learning for Interpretable Natural Language Processing
• Evaluating the Reliability of Self-Explanations in Large Language Models
• Boosting Explainability through Selective Rationalization in Pre-trained Language Models