论文标题
机器阅读理解：上下文化语言模型的作用
Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond
论文作者
论文摘要
机器阅读理解（MRC）旨在教机器阅读和理解人类语言，这是自然语言处理（NLP）的长期目标。随着深度神经网络的爆发和情境化语言模型（CLM）的演变，MRC的研究经历了两个重大突破。 MRC和CLM作为一种现象，对NLP社区产生了重大影响。在这项调查中，我们对MRC进行了全面和比较的综述，涵盖了关于1）MRC和CLM的起源和发展的总体研究主题，特别关注CLM的作用； 2）MRC和CLM对NLP社区的影响； 3）MRC的定义，数据集和评估； 4）从人类认知过程的见解中，一般的MRC架构和技术方法可以看出两阶段编码器解码器解决体系结构； 5）以前的亮点，新兴的主题和我们的经验分析，其中我们特别关注MRC研究不同时期的工作。我们建议对这些主题进行全景分类和新的分类法。我们提出的主要观点是1）MRC提高了从语言处理到理解的进步； 2）MRC系统的快速改善受到CLM的发展的极大收益； 3）MRC的主题正在逐渐从浅层文本匹配到认知推理。
Machine reading comprehension (MRC) aims to teach machines to read and comprehend human languages, which is a long-standing goal of natural language processing (NLP). With the burst of deep neural networks and the evolution of contextualized language models (CLMs), the research of MRC has experienced two significant breakthroughs. MRC and CLM, as a phenomenon, have a great impact on the NLP community. In this survey, we provide a comprehensive and comparative review on MRC covering overall research topics about 1) the origin and development of MRC and CLM, with a particular focus on the role of CLMs; 2) the impact of MRC and CLM to the NLP community; 3) the definition, datasets, and evaluation of MRC; 4) general MRC architecture and technical methods in the view of two-stage Encoder-Decoder solving architecture from the insights of the cognitive process of humans; 5) previous highlights, emerging topics, and our empirical analysis, among which we especially focus on what works in different periods of MRC researches. We propose a full-view categorization and new taxonomies on these topics. The primary views we have arrived at are that 1) MRC boosts the progress from language processing to understanding; 2) the rapid improvement of MRC systems greatly benefits from the development of CLMs; 3) the theme of MRC is gradually moving from shallow text matching to cognitive reasoning.
