基于被引片段识别的科技文摘综述  

Review on Scientific Summary Based on the Recognition of Cited Spans

作　　者：李纲[1] 徐健[1] 余辉 马亚雪 Li Gang;Xu Jian;Yu Hui;Ma Yaxue(Center for Studies of Information Resources,Wuhan University,Wuhan 430072,China;School of Economy and Management,Hubei University of Technology,Wuhan 430064,Hubei,China)

机构地区：[1]武汉大学信息资源研究中心,湖北武汉430072 [2]湖北工业大学经济与管理学院,湖北武汉430064

出　　处：《现代情报》2017年第9期171-176,共6页Journal of Modern Information

基　　金：国家自然科学基金项目"科研团队动态演化规律研究"(项目编号:71273196)

摘　　要：[目的 /意义]基于被引片段识别的科技文摘生成是文献计量学、信息检索和自然语言处理等领域共同关注的研究问题。通过梳理相关成果,可为后续研究提供借鉴。[方法 /过程]本文首先介绍被引片段概念,进而从被引片段识别与分类、文摘生成与评价等步骤对相关研究进行综述。[结果 /结论 ]当前被引片段识别总体上可以分为机器学习和检索两类,分面判定还存在标准不一致的问题,摘要生成与评估方法相关研究较欠缺。[Purpose/significance]Scientific summarization based on reference spans recognition is the common researchquestion in study fi elds such as bibliometrics,information retrieval and natural language processing.By reviewing the related researchachievements,we hope to provide some references for the further research.[Method/process]This paper introduced reference spansconcept and presented and analyzed the latest development of areas such as reference spans recognition,summary facets classifi cationand summary generation and evaluation.[Result/conclusion]At present,the methods of reference spans recognition could be put intotwo types,including methods based on machine learning and methods on retrieval.Th ere were no uniform standards of discourse facetsof abstract.Th e researches on the produce of summary and evaluation methodology were still relatively lacking.

关 键 词：被引片段 科技摘要 引文上下文 

分 类 号：G255.51[文化科学—图书馆学]