| 学术文献引文推荐研究进展 |
| |
| 引用本文： | 陈海华,孟睿,陆伟.学术文献引文推荐研究进展[J].图书情报工作,2015,59(15):133. |
| |
| 作者姓名： | 陈海华 孟睿 陆伟 |
| |
| 作者单位： | 武汉大学信息管理学院 武汉 430072;武汉大学信息检索与知识挖掘研究所 武汉 430072 |
| |
| 基金项目： | 本文系国家自然科学基金面上项目"面向词汇功能的学术文本语义识别与知识图谱构建"(项目编号:71473183)研究成果之一。 |
| |
| 摘 要： | 目的/意义]学术文献引文推荐是指对于给定的学术文献,自动化地为其推荐合适的引文和参考文献。借助于引文推荐,用户可以在一定程度上提高撰写学术文献的效率,降低对重要相关文献的漏引。方法/过程]分析国内外引文推荐研究的最新进展,阐述引文推荐问题的演化过程,从局部引文推荐和全局引文推荐等方面对引文推荐进行梳理,重点归纳文档相似性、主题模型、翻译模型、协同过滤和混合推荐等5种引文推荐常用方法,并总结引文推荐常用数据集和测评方法。结果/结论]已有引文推荐研究的主要问题在于未考虑用户偏好的动态变化性及研究领域的综合性,在用户研究和实际应用方面仍有所欠缺;未来引文推荐的研究可运用语义化表达方法和自然语言生成技术,从基于上下文的引文推荐和跨语言引文推荐等方面进行展开。
|
| 关 键 词： | 引文推荐 引文推荐分类 引文推荐方法 引文上下文 |
| 收稿时间： | 2015-06-09 |
Research Review on Citation Recommendation of Academic Literatures |
| |
| Chen Haihua,Meng Rui,Lu Wei.Research Review on Citation Recommendation of Academic Literatures[J].Library and Information Service,2015,59(15):133. |
| |
| Authors: | Chen Haihua Meng Rui Lu Wei |
| |
| Institution: | School of Information Management, Wuhan University, Wuhan 430072; Institute for Information Retrieval and Knowledge Mining, Wuhan University, Wuhan 430072 |
| |
| Abstract: | Purpose/significance] Citation Recommendation of academic literature refers to automatically recommend suitable citations and references for a given paper. With the aid of citation recommendation, authors can improve the efficiency of writing academic literatures and avoid missing important relevant literatures.Method/process] This paper analyzesthe latest development of researches on citation recommendation at home and abroad, describes the evolution of citation recommendation, and elaborates the citation recommendationfromdifferent perspectives, such asthe local citation recommendation and global citation recommendation. Main citation recommendation techniques including text similarity, topic model, translation model, collaborative filtering and hybrid recommendation are reviewed. Also, several major data-sets and evolution methods on citation recommendation are summarized.Result/conclusion] Previous researches didn't consider the dynamic tendency of user's preference and the comprehensiveness of research area. What's more, user studies and practical applications of citation recommendation are still lacking. To fill the gap, future works on citation recommendation may focus on semantic expression, natural language generation and cross-language citation recommendation. |
| |
| Keywords: | citation recommendation citation recommendation classification citation recommendation method citation context |
|
| 点击此处可从《图书情报工作》浏览原始摘要信息 |
| 点击此处可从《图书情报工作》下载免费的PDF全文 |
|
