论文标题
对机器阅读理解中的任务和模型的研究
A Study of the Tasks and Models in Machine Reading Comprehension
论文作者
论文摘要
为了提供有关机器阅读理解中现有任务和模型（MRC）的调查，本报告回顾了：1）一些代表性的简单且复杂的MRC任务的数据集收集和绩效评估； 2）建筑设计，注意机制和促进性能的方法，用于开发基于神经网络的MRC模型； 3）最近提出的一些转移学习方法将外部语料库中包含的文本风格知识纳入MRC模型的神经网络； 4）最近提出的一些知识库编码方法将外部知识库中包含的图形知识纳入MRC模型的神经网络。此外，根据已经取得的成就和仍然不足的事情，该报告还为未来的研究提出了一些开放问题。
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.
