基于深度学习的机器阅读理解研究综述

机器阅读理解任务在近年来备受关注，它赋予计算机从文本数据中获取知识和回答问题的能力。如何让机器理解自然语言是人工智能领域长期存在的挑战之一，近年来大规模高质量数据集的发布和深度学习技术的运用，使得机器阅读理解取得了快速发展。基于神经网络的端到端的模型结构，基于预训练语言模型以及推理技术的应用，其性能在大规模评测数据集上有很大提升，但距离真正的理解语言还有较大差距。本文对机器阅读理解任务的研究现状与发展趋势进行了综述，主要包括任务划分、机器阅读理解模型与相关技术的分析，特别是基于知识推理的机器阅读理解技术，总结并讨论了该领域的发展趋势。

Survey of machine reading comprehension based on deep learning

In recent years, there has been a great deal of interest in the task of machine reading comprehension. It enables computers to learn and answer questions based on text input. One of the long-standing challenges in the field of artificial intelligence is how to make machines understand natural language. In recent years, machine reading comprehension has advanced rapidly as a result of the large-scale release of high-quality data sets and the application of deep learning technology. The use of an end-to-end model structure based on neural networks, a pre-trained language model, and reasoning technology has greatly improved their performance on large-scale evaluation data sets. However, there is still a big gap in real language understanding. This paper summarizes the research status and development trend of machine reading comprehension tasks, including division of tasks, analysis of machine reading comprehension model and related technologies, particularly machine reading comprehension technology based on knowledge reasoning, and finally discusses the development trend in this field.