Exploring author name disambiguation on PubMed-scale

被引:28
作者
Song, Min [1 ]
Kim, Erin Hea-Jin [1 ]
Kim, Ha Jin [1 ]
机构
[1] Yonsei Univ, Dept Lib & Informat Sci, Seoul 120749, South Korea
关键词
Author name disambiguation; Named entity recognition; Keyphrase extraction; Machine learning; PubMed; MODEL;
D O I
10.1016/j.joi.2015.08.004
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Author name disambiguation (AND) creates a daunting challenge in that disambiguation techniques often draw false conclusions when applied to incomplete or incorrect publication data. It becomes a more critical issue in the biomedical domain where PubMed articles are written by a wide range of researchers internationally. To tackle this issue, we create a carefully hand-crafted training set drawn from the entire PubMed collection by going through multiple iterations. We assess the quality of our training set by comparing it with SCOPUS-based training set. In addition, for the performance enhancement of the AND techniques, we propose a new set of publication features extracted by text mining techniques. The results of the experiments show that all four supervised learning techniques (Random Forest, C4.5, KNN, and SVM) with the new publication features (called NER model) achieve improved performance over the baseline and hybrid edit distance model. (C) 2015 Elsevier Ltd. All rights reserved.
引用
收藏
页码:924 / 941
页数:18
相关论文
共 38 条
[1]  
[Anonymous], P 9 ACM IEEE CS JOIN
[2]  
[Anonymous], 2003, P IJCAI 2003 WORKSH
[3]  
[Anonymous], P 6 ACM IEEE CS JOIN
[4]  
[Anonymous], RES ADV TECHNOLOGY D
[5]  
[Anonymous], MACHINE LEARNING KNO
[6]  
[Anonymous], 2011, Journal of Information and Data Management
[7]  
[Anonymous], P 23 INT C COMP LING
[8]  
[Anonymous], P 2004 JOINT ACM IEE
[9]  
[Anonymous], 2010, P 10 ANN JOINT C DIG, DOI 10.1145/1816123.1816130
[10]  
[Anonymous], 2020, CODE VIRGINIA