模式识别与人工智能
Friday, Apr. 4, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2021, Vol. 34 Issue (6): 485-496    DOI: 10.16451/j.cnki.issn1003-6059.202106001
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Name Disambiguation Based on Heterogeneous Network Representation Learning
TANG Zhengzheng1,2, HONG Xuehai2,3, WANG Yang1,2, LI Yuxuan1,2
1. Center of Information Development Strategy and Evaluation, Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190
2. School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049
3. Strategy Research Center of Information Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190

Download: PDF (1147 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  During the search for the name of an author in the system, the return of all documents of the author deteriorates the user experience. Name disambiguation can improve the retrieval accuracy. Therefore, a name disambiguation method based on heterogeneous network representation learning is proposed. Firstly, a paper heterogeneous network is constructed for each ambiguous name. Then, the representation vector of each paper node in the network is obtained based on the heterogeneous network and the Word2Vec. Finally, papers are divided up and assigned to different author entities via rule matching and a clustering method based on density with noise. The proposed method generates better performance on OAG-WholsWho competition dataset, and its effectiveness is verified.
Key wordsName Disambiguation      Heterogeneous Network      Word to Vector(Word2Vec)      Classification Algorithm     
Received: 08 March 2021     
ZTFLH: TP 391.41  
Fund:National Natural Science Foundation of China(No.92046017), Information Engineering Project of Chinese Academy of Sciences(No.XXH13504-03)
Corresponding Authors: HONG Xuehai, Ph.D., professor. His research interests include high performance computing, big data and cloud computing, and artificial intelligence.   
About author:: TANG Zhengzheng, Ph.D. candidate. His research interests include machine learning, data mining and graph representation lear-ning.
WANG Yang, Ph.D., senior engineer. His research interests include informatization development strategy research, big data analysis and situational awareness system.
LI yuxuan, master student. His research interests include machine learning and information retrieval.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
TANG Zhengzheng
HONG Xuehai
WANG Yang
LI Yuxuan
Cite this article:   
TANG Zhengzheng,HONG Xuehai,WANG Yang等. Name Disambiguation Based on Heterogeneous Network Representation Learning[J]. , 2021, 34(6): 485-496.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202106001      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2021/V34/I6/485
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn