Awesome Natural Language Explanation

The following is a collections of work related to free-text natural language explanations, also called abstractive rationales.

• Awesome Natural Language Explanation
  • papers
    • survey papers
    • general
    • datasets
  • books
  • tutorials
  • related repositories

papers

survey papers

Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing

Local Interpretations for Explainable Natural Language Processing: A Survey

Interpreting Deep Learning Models in Natural Language Processing: A Review

general

WT5?! Training Text-to-Text Models to Explain their Predictions https://arxiv.org/pdf/2004.14546.pdf

Generating Counterfactual Explanations with Natural Language

Explaining Question Answering Models through Text Generation

Unsupervised Commonsense Question Answering with Self-Talk

When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data

Rationale-Inspired Natural Language Explanations with Commonsense

Exploiting Rationale Data for Explainable NLP Models

Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?

Few-Shot Self-Rationalization with Natural Language Prompts

Cross-Domain Transfer of Generative Explanations Using Text-to-Text Models

Prompting Contrastive Explanations for Commonsense Reasoning Task

Does External Knowledge Help Explainable Natural Language Inference? Automatic Evaluation vs. Human Ratings

Story Generation with Commonsense Knowledge Graphs and Axioms

NILE : Natural Language Inference with Faithful Natural Language Explanations

LIREx: Augmenting Language Inference with Relevant Explanation

Generate Natural Language Explanations for Recommendation

datasets

e-SNLI: Natural Language Inference with Natural Language Explanations

Explain Yourself! Leveraging Language Models for Commonsense Reasoning

QED: A Framework and Dataset for Explanations in Question Answering

ERASER: A Benchmark to Evaluate Rationalized NLP Models

A Study of Automatic Metrics for the Evaluation of Natural Language Explanations

Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering

books

Explainable Natural Language Processing, Anders Søgaard

tutorials

Explainability for Natural Language Processing Lecture-style Tutorial at SIGKDD 2021

related repositories

Awesome-explainable-AI

awesome-machine-learning-interpretability

awesome-nlg