Neural Machine Reading Comprehension: Methods and Trends
arXiv:1907.01118 · doi:10.1016/j.apsusc.2018.11.214
Abstract
Machine reading comprehension (MRC), which requires a machine to answer questions based on a given context, has attracted increasing attention with the incorporation of various deep-learning techniques over the past few years. Although research on MRC based on deep learning is flourishing, there remains a lack of a comprehensive survey summarizing existing approaches and recent trends, which motivated the work presented in this article. Specifically, we give a thorough review of this research field, covering different aspects including (1) typical MRC tasks: their definitions, differences, and representative datasets; (2) the general architecture of neural MRC: the main modules and prevalent approaches to each; and (3) new trends: some emerging areas in neural MRC as well as the corresponding challenges. Finally, considering what has been achieved so far, the survey also envisages what the future may hold by discussing the open issues left to be addressed.
arXiv comment46 pages
References in corpus (48)
- Distributed Representations of Words and Phrases and their Compositionality
- Neural Machine Translation by Jointly Learning to Align and Translate
- Van der Waals heterostructures
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Teaching Machines to Read and Comprehend
- New Perspectives for Rashba Spin-Orbit Coupling
- A generic new platform for topological quantum computation using semiconductor heterostructures
- Bidirectional Attention Flow for Machine Comprehension
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- Giant Spin-splitting in the Bi/Ag(111) Surface Alloy
- Experimental demonstration of the topological surface states protected by the time-reversal symmetry
- Strong spin-orbit splitting on Bi surfaces
- End-To-End Memory Networks
- Highway Networks
- Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
- The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
- Dynamic Coattention Networks For Question Answering
- Machine Comprehension Using Match-LSTM and Answer Pointer
- QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
- Manipulation of the large Rashba spin splitting in polar two-dimensional transition metal dichalcogenides
- Electrons and phonons in single layers of hexagonal indium chalcogenides from ab initio calculations
- SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
- ReasoNet: Learning to Stop Reading in Machine Comprehension
- Giant tunable Rashba spin splitting in two-dimensional BiSb monolayer and BiSb/AlN heterostructures
- Topological surface state under graphene for two-dimensional spintronics in air
- Ideal two-dimensional electron systems with a giant Rashba-type spin splitting in real materials: surfaces of bismuth tellurohalides
- Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
- Quasar: Datasets for Question Answering by Search and Reading
- A Review on Flexural Mode of Graphene: Lattice Dynamics, Thermal Conduction, Thermal Expansion, Elasticity, and Nanomechanical Resonance
- SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering
- Multi-Perspective Context Matching for Machine Comprehension
- Rashba spin-orbit coupling and spin relaxation in silicon quantum wells
- DCN+: Mixed Objective and Deep Residual Coattention for Question Answering
- MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge
- MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension
- Embracing data abundance: BookTest Dataset for Reading Comprehension
- Words or Characters? Fine-grained Gating for Reading Comprehension
- End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension
- Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
- Iterative Alternating Neural Attention for Machine Reading
- U-Net: Machine Reading Comprehension with Unanswerable Questions
- Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions
- A Comparative Study of Word Embeddings for Reading Comprehension
- A Survey on Neural Machine Reading Comprehension
- Smarnet: Teaching Machines to Read and Comprehend Like Human
- Bi-directional Attention with Agreement for Dependency Parsing
- HAS-QA: Hierarchical Answer Spans Model for Open-domain Question Answering
- Knowledge Based Machine Reading Comprehension