A Survey on Explainability in Machine Reading Comprehension
arXiv:2010.00389
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 (19)
- Deep Learning for Answer Sentence Selection
- Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering
- Question Answering as Global Reasoning over Semantic Abstractions
- Neural Module Networks for Reasoning over Text
- Dynamically Fused Graph Network for Multi-hop Reasoning
- Machine Reading Comprehension: a Literature Review
- Cognitive Graph for Multi-Hop Reading Comprehension at Scale
- A Survey on Neural Machine Reading Comprehension
- 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
- Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network
- Answering Complex Open-domain Questions Through Iterative Query Generation
- Explore, Propose, and Assemble: An Interpretable Model for Multi-Hop Reading Comprehension
- Multi-Hop Paragraph Retrieval for Open-Domain Question Answering
- Do Multi-hop Readers Dream of Reasoning Chains?
- Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning
- A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction
- Repurposing Entailment for Multi-Hop Question Answering Tasks
- NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language