参考文献格式规范性检测方法研究  

Method for bibliographic reference format normativity checking

作　　者：耿思 李宁[1,2] 赵林[1,2] 

机构地区：[1]北京信息科技大学网络文化与数字传播北京市重点实验室,北京100101 [2]北京信息科技大学计算机学院,北京100101

出　　处：《北京信息科技大学学报（自然科学版）》2017年第1期44-49,59,共7页Journal of Beijing Information Science and Technology University

基　　金：国家自然科学基金资助项目(61672105);国家高科技研究发展计划(863计划)资助项目(2015AA015403)

摘　　要：为了解决在文献类型标志缺失的情况下无法对参考文献格式规范性检查的问题,提出了一种基于规则的参考文献格式规范性检测方法。首先从参考文献中提取各个著录项,在此基础上通过机器学习构建决策树,然后利用决策规则判断参考文献类型,最后根据文献类型调用相应的Schema规则进行格式检查。实验结果表明,该算法能够有效检测参考文献格式的规范性,对于参考文献的有效利用具有重要意义。To solve the problem that the correctness of bibliography are unable to be checked in the absence of bibliographic types,a method of bibliographic reference format normativity checking based on rules is put forward. First,the bibliographic items are extracted from the references,and the decision tree is constructed by machine learning. Then the decision rules are applied to determine bibliographic types. Finally,the format of bibliography can be checked according to the bibliographic type to call the corresponding Schema rules. Experiments showed that the proposed method can effectively check the format of bibliography,which lay the foundation for the effective use of references.

关 键 词：参考文献格式检查 参考文献规范性 著录项提取 文献类型判定 决策树 

分 类 号：TP302[自动化与计算机技术—计算机系统结构]