基于逻辑推理的机器阅读理解综述
Survey of Machine Reading Comprehension Based on Logical Reasoning
摘要
Abstract
Machine reading comprehension is one of the core tasks in the field of natural language processing,the goal of which is to enable machines to understand natural language text and correctly answer questions about the content of the text.With the development of methods and models related to natural language processing,researchers have begun to focus on the more challenging inferential problems in machine reading comprehension,which often require models to not only understand superficial information in text,but also to be able to think and reason logically to answer more complex questions.This paper gives a comprehensive summary of the latest achievements of machine reading comprehension based on logical reasoning.Firstly,the task of machine reading comprehension based on logical reasoning is introduced.Secondly,this paper introduces relevant methods for this task and classifies them into four categories based on different focuses:methods based on symbolic neural networks,methods based on graph neural networks,methods based on pre-training,and fine-tuning strategies based on large models,with a focus on describing the representative work of the four methods.Finally,the advantages and disadvantages of the methods are discussed on LogiQA and ReClor datasets,and the future research directions of machine reading comprehension task based on logical reasoning are summarized.关键词
机器阅读理解/逻辑推理/智能问答Key words
machine reading comprehension/logical reasoning/intelligent questions and answers分类
信息技术与安全科学引用本文复制引用
李晴,李艳玲,董杰,葛凤培,林民..基于逻辑推理的机器阅读理解综述[J].计算机科学与探索,2024,18(8):1998-2013,16.基金项目
国家自然科学基金(12204062,62266033,61806103,61562068) （12204062,62266033,61806103,61562068）
无穷维哈密顿系统及其算法应用教育部重点实验室开放课题(2023KFZD03) （2023KFZD03）
内蒙古自然科学基金(2022LHMS06001) （2022LHMS06001）
内蒙古师范大学基本科研业务费专项资金(2022JBQN106,2022JBQN111,2022JBTD016) （2022JBQN106,2022JBQN111,2022JBTD016）
内蒙古自治区高等学校创新团队发展计划(NMGIRT2407) （NMGIRT2407）
内蒙古师范大学研究生创新基金(CXJJS23066) （CXJJS23066）
"一区两基地"建设项目(计算科学联合创新实验室). This work was supported by the National Natural Science Foundation of China(12204062,62266033,61806103,61562068),the Proj-ect of Key Laboratory of Infinite-Dimensional Hamiltonian System and Its Algorithm Application(Inner Mongolia Normal University),Ministry of Education(2023KFZD03),the Natural Science Foundation of Inner Mongolia(2022LHMS06001),the Fundamental Re-search Funds for Inner Mongolia Normal University(2022JBQN106,2022JBQN111,2022JBTD016),the Program for Innovative Re-search Team in Universities of Inner Mongolia Autonomous Region(NMGIRT2407),the Innovation Fund for Postgraduates of Inner Mongolia Normal University(CXJJS23066),and the"One District,Two Bases"Construction Project(Joint Innovation Laboratory of Computing Science). （计算科学联合创新实验室）
