{"title":"Citation recommendation based on argumentative zoning of user queries","authors":"Shutian Ma , Chengzhi Zhang , Heng Zhang , Zheng Gao","doi":"10.1016/j.joi.2024.101607","DOIUrl":null,"url":null,"abstract":"<div><div>Citation recommendation aims to locate the important papers for scholars to cite. When writing the citing sentences, the authors usually hold different citing intents, which are referred to citation function in citation analysis. Since argumentative zoning is to identify the argumentative and rhetorical structure in scientific literature, we want to use this information to improve the citation recommendation task. In this paper, a multi-task learning model is built for citation recommendation and argumentative zoning classification. We also generated an annotated corpus of the data from PubMed Central based on a new argumentative zoning schema. The experimental results show that, by considering the argumentative information in the citing sentence, citation recommendation model will get better performance.</div></div>","PeriodicalId":48662,"journal":{"name":"Journal of Informetrics","volume":"19 1","pages":"Article 101607"},"PeriodicalIF":3.4000,"publicationDate":"2024-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Informetrics","FirstCategoryId":"91","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1751157724001196","RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0
Abstract
Citation recommendation aims to locate the important papers for scholars to cite. When writing the citing sentences, the authors usually hold different citing intents, which are referred to citation function in citation analysis. Since argumentative zoning is to identify the argumentative and rhetorical structure in scientific literature, we want to use this information to improve the citation recommendation task. In this paper, a multi-task learning model is built for citation recommendation and argumentative zoning classification. We also generated an annotated corpus of the data from PubMed Central based on a new argumentative zoning schema. The experimental results show that, by considering the argumentative information in the citing sentence, citation recommendation model will get better performance.
引文推荐的目的是为学者们找到需要引用的重要文献。在撰写引文时，作者通常持有不同的引文意图，这在引文分析中被称为引文功能。由于论证分区是为了识别科学文献中的论证和修辞结构，因此我们希望利用这些信息来改进引文推荐任务。本文建立了一个用于引文推荐和论证分区分类的多任务学习模型。我们还根据新的论证分区模式从 PubMed Central 中生成了一个数据注释语料库。实验结果表明，通过考虑引文句子中的论证信息，引文推荐模型将获得更好的性能。
期刊介绍：
Journal of Informetrics (JOI) publishes rigorous high-quality research on quantitative aspects of information science. The main focus of the journal is on topics in bibliometrics, scientometrics, webometrics, patentometrics, altmetrics and research evaluation. Contributions studying informetric problems using methods from other quantitative fields, such as mathematics, statistics, computer science, economics and econometrics, and network science, are especially encouraged. JOI publishes both theoretical and empirical work. In general, case studies, for instance a bibliometric analysis focusing on a specific research field or a specific country, are not considered suitable for publication in JOI, unless they contain innovative methodological elements.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
