Towards Effective Author Name Disambiguation by Hybrid Attention

作     者：Qian Zhou Wei Chen Peng-Peng Zhao An Liu Jia-Jie Xu Jian-Feng Qu Lei Zhao 周乾;陈伟;赵朋朋;刘安;许佳捷;瞿剑峰;赵雷

作者机构：School of Computer Science and TechnologySoochow UniversitySuzhou 215006China 

出 版 物：《Journal of Computer Science & Technology》 (计算机科学技术学报（英文版）)

年 卷 期：2024年第39卷第4期

页      面：929-950页

核心收录：

学科分类：07[理学] 0701[理学-数学] 070101[理学-基础数学] 

基　　金：supported by the Major Program of the Natural Science Foundation of Jiangsu Higher Education Institutions of China under Grant Nos.19KJA610002 and 19KJB520050 the National Natural Science Foundation of China under Grant No.61902270 

主　　题：author name disambiguation multiple-feature information hybrid attention pruning strategy structural information loss of vector space 

摘      要：Author name disambiguation(AND)is a central task in academic search,which has received more attention recently accompanied by the increase of authors and academic *** tackle the AND problem,existing studies have proposed various approaches based on different types of information,such as raw document features(e.g.,co-authors,titles,and keywords),the fusion feature(e.g.,a hybrid publication embedding based on multiple raw document features),the local structural information(e.g.,a publication s neighborhood information on a graph),and the global structural information(e.g.,interactive information between a node and others on a graph).However,there has been no work taking all the above-mentioned information into account and taking full advantage of the contributions of each raw document feature for the AND problem so *** fill the gap,we propose a novel framework named EAND(Towards Effective Author Name Disambiguation by Hybrid Attention).Specifically,we design a novel feature extraction model,which consists of three hybrid attention mechanism layers,to extract key information from the global structural information and the local structural information that are generated from six similarity graphs constructed based on different similarity coefficients,raw document features,and the fusion *** hybrid attention mechanism layer contains three key modules:a local structural perception,a global structural perception,and a feature ***,the mean absolute error function in the joint loss function is used to introduce the structural information loss of the vector *** results on two real-world datasets demonstrate that EAND achieves superior performance,outperforming state-of-the-art methods by at least+2.74%in terms of the micro-F1 score and+3.31%in terms of the macro-F1 score.