A Study of the Tasks and Models in Machine Reading Comprehension

TL;DR

This paper surveys existing datasets, models, and techniques in Machine Reading Comprehension, highlighting recent advances in neural architectures, transfer learning, and knowledge base integration, while also discussing open challenges for future research.

Contribution

It provides a comprehensive overview of MRC tasks, models, and recent methods like transfer learning and knowledge base encoding, identifying gaps and future directions.

Findings

Analysis of dataset collection and evaluation methods

Review of neural network architectures and attention mechanisms

Discussion of transfer learning and knowledge base integration approaches

Abstract

To provide a survey on the existing tasks and models in Machine Reading Comprehension (MRC), this report reviews: 1) the dataset collection and performance evaluation of some representative simple-reasoning and complex-reasoning MRC tasks; 2) the architecture designs, attention mechanisms, and performance-boosting approaches for developing neural-network-based MRC models; 3) some recently proposed transfer learning approaches to incorporating text-style knowledge contained in external corpora into the neural networks of MRC models; 4) some recently proposed knowledge base encoding approaches to incorporating graph-style knowledge contained in external knowledge bases into the neural networks of MRC models. Besides, according to what has been achieved and what are still deficient, this report also proposes some open problems for the future research.