A Survey on Explainability in Machine Reading Comprehension

Abstract

This paper presents a systematic review of benchmarks and approaches for explainability in Machine Reading Comprehension (MRC). We present how the representation and inference challenges evolved and the steps which were taken to tackle these challenges. We also present the evaluation methodologies to assess the performance of explainable systems. In addition, we identify persisting open research questions and highlight critical directions for future work.

References in corpus (42)

• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• A large annotated corpus for learning natural language inference
• Deep Learning for Answer Sentence Selection
• e-SNLI: Natural Language Inference with Natural Language Explanations
• Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• Question Answering via Integer Programming over Semi-Structured Knowledge
• Multi-hop Question Answering via Reasoning Chains
• Question Answering as Global Reasoning over Semantic Abstractions
• Neural Module Networks for Reasoning over Text
• Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
• Explaining Question Answering Models through Text Generation
• Dynamically Fused Graph Network for Multi-hop Reasoning
• Is Graph Structure Necessary for Multi-hop Question Answering?
• Abductive Commonsense Reasoning
• Hierarchical Graph Network for Multi-hop Question Answering
• Machine Reading Comprehension: a Literature Review
• Efficient and Robust Question Answering from Minimal Context over Documents
• Cognitive Graph for Multi-Hop Reading Comprehension at Scale
• Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering
• A Survey on Neural Machine Reading Comprehension
• Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
• Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents
• Red Dragon AI at TextGraphs 2019 Shared Task: Language Model Assisted Explanation Generation
• Answering Complex Questions Using Open Information Extraction
• Commonsense for Generative Multi-Hop Question Answering Tasks
• Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network
• Answering Complex Open-domain Questions Through Iterative Query Generation
• On the Possibilities and Limitations of Multi-hop Reasoning Under Linguistic Imperfections
• Multi-Step Inference for Reasoning Over Paragraphs
• Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension
• Multi-Hop Paragraph Retrieval for Open-Domain Question Answering
• Evidence Sentence Extraction for Machine Reading Comprehension
• Do Multi-hop Readers Dream of Reasoning Chains?
• Natural Language QA Approaches using Reasoning with External Knowledge
• A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction
• Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning
• Repurposing Entailment for Multi-Hop Question Answering Tasks
• NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
• Learning to Recover Reasoning Chains for Multi-Hop Question Answering via Cooperative Games
• R3: A Reading Comprehension Benchmark Requiring Reasoning Processes

Cited by in corpus (7)

• Rationalization for Explainable NLP: A Survey
• Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning
• ExplanationLP: Abductive Reasoning for Explainable Science Question Answering
• Case-Based Abductive Natural Language Inference
• Do Natural Language Explanations Represent Valid Logical Arguments? Verifying Entailment in Explainable NLI Gold Standards
• Encoding Explanatory Knowledge for Zero-shot Science Question Answering
• Machine Reading Comprehension using Case-based Reasoning