A Survey on Explainability in Machine Reading Comprehension

2020/10/01 by Mokanarangan Thayaparan, Thayaparan, Mokanarangan, Marco Valentino +3 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Intelligent Tutoring Systems and Adaptive Learning #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2010.00389

openalex publication_date 2020/10/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Deep Learning for Answer Sentence Selection
• SQuAD: 100,000+ Questions for Machine Comprehension of Text
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Efficient and Robust Question Answering from Minimal Context over Documents
• e-SNLI: Natural Language Inference with Natural Language Explanations
• Cognitive Graph for Multi-Hop Reading Comprehension at Scale
• A Survey on Neural Machine Reading Comprehension
• Commonsense for Generative Multi-Hop Question Answering Tasks
• NLProlog: Reasoning with Weak Unification for Question Answering in\n Natural Language
• Multi-Hop Paragraph Retrieval for Open-Domain Question Answering
• HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
• A large annotated corpus for learning natural language inference
• Repurposing Entailment for Multi-Hop Question Answering Tasks
• Machine Reading Comprehension: a Literature Review
• A Survey of Methods for Explaining Black Box Models
• Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning
• Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
• Multi-hop Question Answering via Reasoning Chains
• Answering Complex Open-domain Questions Through Iterative Query Generation
• Do Multi-hop Readers Dream of Reasoning Chains?
• Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network
• Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
• R3: A Reading Comprehension Benchmark Requiring Reasoning Processes
• Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering
• Explaining Question Answering Models through Text Generation
• On the Possibilities and Limitations of Multi-hop Reasoning Under Linguistic Imperfections
• Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
• A Framework for Evaluation of Machine Reading Comprehension Gold Standards

Cited by

• Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder

Related

• Unsupervised Explanation Generation for Machine Reading Comprehension
• Benchmarking Machine Reading Comprehension: A Psychological Perspective
• A Survey on Machine Reading Comprehension Systems
• A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasets
• A Study of the Tasks and Models in Machine Reading Comprehension