Jie Tang (唐杰)

 

Assistant Professor, IEEE Member, ACM Professional Member.

Department of Computer Science and Technology, Tsinghua University

 

Work Phone Number:          +8610-62788788-18

Office Address:                     1-308, FIT Building, Tsinghua University, Beijing, 100084. China PR.

E-Mail Address:                 abcd

My Blog:                                Jie Tang’s Blog

My FOAF:                             Jie Tang’s FOAF

My ArnetMiner Page:          Jie Tang’s Arnet

 

 

 

I am now a visiting scholar at Department of Computer Science and Engineering of Hong Kong University of Science and Technology.

I am an assistant professor in Department of Computer Science and Technology of Tsinghua University. I obtained my Ph.D. in DCST of Tsinghua University in 2006. I became ACM Professional member in 2006 and IEEE member in 2007.

 

During my graduate career, I have been an intern at NLC group of Microsoft Research Asia from 2004 to 2005. I also have attended the internship program of IBM China Research Lab in 2004.

 

I am interested in social network mining/text mining and semantic web (especially semantic annotation and ontology mapping).

 

New ** ArnetMiner 3.0 is online!! **, April, 2008

ArnetMiner 2.0 is online!, July, 2007

RESEARCH PROJECTS

·      Scalable Algorithms for Message Tagging and Community Discovery. (2008-2009). Tsinghua-Google Joint Research Project funded by Google Research (Major Member).

·      Research of Semantic Content Annotation. (2008-2010). Chinese Young Faculty Research Funding under Grant No. 20070003093 (PI).

·      Social Search in Web Community. (2008-2009). Joint Research Project funded by IBM China Research Lab (PI).  In this project, we jointly study how to combine the human intelligence with computer algorithms for improve the search quality. We also consider how to model the tagging and the timely information in the social search model.

·      Research of Unified Models for Semantic Content Annotation. (2008-2010). NSFC Funded Project under Grant No. 60703059 (PI). The project addresses the semantic content annotation and semantic relationship extraction. Specifically, we will focus on studying different Markov random fields (e.g., Tree-structured Conditional Random Fields) for extracting and annotating the semantic instance and semantic relationship. We plan to apply the proposed models to a real-world social network system, ArnetMiner.

·      Requirement Engineering Validation and Management. (2007-2012). National Foundational Science Research (973) under Grant No. 2007CB310803. (Major member).

·      Expertise Oriented Mining for Web Community. (2007-2008). Minnesota/China Collaborative Research Program jointly funded by University of Minnesota and Tsinghua University (PI and co-PI with Prof. Loren Terveen).  In this research project, we will jointly study the new expertise oriented mining issues in the area of Web-based social networks. Specifically, we will focus on investigating three sub-topics, namely structured data extraction, information integration, and expertise search.

·      Semantic Web-based Social Network Mining. (2007-2009). Research project funded by Tsinghua University (PI). In this project, we will focus on studying mining issues in the Semantic Web-based social network. Specifically, we will focus on integrating different Web-based social networks into a unique Semantic Web-based social network; we will investigate the name disambiguation problem; we will also study the trust problem in the Semantic Web-based social network.

·      Text Mining for Web 2.0. (2007-2008). Joint Research Project funded by IBM China Research Lab (PI).  In this research project, we jointly study the new techniques in the area of Text Mining for Web 2.0. Specifically, we will focus on investigating new mining issues on structured and un-structured data (e.g. social network mining). We have developed a prototype system: ArnetMiner.

·      Research of Semantic Web Content Availability. (2007-2008). Research project funded by DCST, Tsinghua University (PI). In this project, we focus on investigating new sequential labeling models for semantic annotation and new supervised machine learning methods for ontology alignment.

·      Information Sharing and Recommendation in Web Community. (2006-2008). Project funded by International cooperation (PI). http://www.powazi.com/.

·      Toward Managing Semantic Web Content. (2007-). Joint Research Project funded by IBM China Research Lab (co-PI with Prof. Juanzi Li). In this project, we will apply advanced Semantic Web technologies and integrated development environments to manipulate semantic information so as to simplify managing Semantic Web Content. We will use ontology to represent, organize, and manage the content of resources from different sources including database, web pages, and plain text.

·      Research of Key Technologies and their Application in Domain-specific Semantic Web Content Management. (2006-2008). NSFC Funded Project under Grant No. 90604025 (Major member). The project addresses semantic annotation, ontology mapping, and semantic content management (e.g. semantic retrieval, semantic data visualization, etc.). We have developed a prototype system called SWARMS (Semantic Web Aided Rich Mining System), an ontology alignment tool called RiMOM (Risk Minimization based Ontology Mapping), and several semantic annotation tools.

·      Semantic Web, Ontology, Granularity and Distributed Ontology System. (2003-2004). A project funded by National Natural Scientific Funding under Grant No. 60443002 (Major member). In this project, I focused on investigating new information extraction methods for semantic web annotation and new matching methods for ontology mapping.

·      Advanced Semantic Web Technologies to Support Ontology based Enterprise Content Management. (2006-2008). A project funded by China-Greece Academic Research Funding (Major member). In this project, we are aimed at employing information extraction and information integration methods in enterprise content management. Specifically, we try to extract information from different formats of documents. We also try to integrate information from different data sources.

·      TIPSI (The Intelligence Processor of Semi-structured Information). (2002-2005). A project funded by International Cooperation with ITF Frontier (Major member). TIPSI is aimed at extracting complex information from semi-structured information. Enterprise annual reports from ShangHai Stock Exchange are used as experimental data. The reports are first converted into a uniform format in XML, and then are passed into a process of semi-automatic extraction; finally result into a semantic view.

 

PUBLICATIONS

2008

l  Jie Tang, Jing Zhang, Limin Yao, Juanzi Li, Li Zhang, and Zhong Su. ArnetMiner: Extraction and Mining of Academic Social Networks. In Proceedings of the Fourteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD’2008). [PDF]

l  Limin Yao, Jie Tang, and Juanzi Li. The Entire Solution Path for Support Vector Machine in Positive and Unlabeled Classification. Journal of Tsinghua Science and Technology. (accepted) [PDF]

l  Jing Zhang, Jie Tang, Bangyong Liang, Zi Yang, Sijie Wang, Jingjing Zuo, and Juanzi Li. Recommendation over a Heterogeneous Social Network. In Proceedings of the 9th International Conference on Web-Age Information Management (WAIM’2008). (to appear) [PDF]

l  Yize Li and Jie Tang. Expertise Search in a Time-varying Social Network. In Proceedings of the 9th International Conference on Web-Age Information Management (WAIM’2008). (to appear) [PDF]

l  Feng Wang, Juanzi Li, Jie Tang, Jing Zhang, and Kehong Wang. Name Disambiguation Using Atomic Clusters. In Proceedings of the 9th International Conference on Web-Age Information Management (WAIM’2008). (to appear) [PDF]

l  Qian Zhong, Juanzi Li, Jie Tang, Yi Li, and Lizhu Zhou. Path similarity based Directory Ontology Matching. In Proceedings of the 9th International Conference on Web-Age Information Management (WAIM’2008). (to appear)

l  Juanzi Li, Gui-rong Xue, Jie Tang, and Ying Ding. WWW 2008 workshop on social web search and mining: SWSM2008. In Proceedings of the 17th International World Wide Web Conference (WWW2008). ACM Press. pp. 1281-1282.

l  Jie Tang, Jing Zhang, Duo Zhang, and Juanzi Li. A Unified Framework for Name Disambiguation. (Poster Paper). In Proceedings of the 17th International World Wide Web Conference (WWW2008). ACM Press. pp. 1205-1206. [PDF]

l  Jie Tang, Jing Zhang, Limin Yao, and Juanzi Li. Extraction and Mining of an Academic Social Network. (Poster Paper). In Proceedings of the 17th International World Wide Web Conference (WWW2008). ACM Press. pp. 1193-1194. [PDF]

l  Juanzi Li, Jie Tang, Jing Zhang, Qiong Luo, Yunhao Liu and Mingcai Hong, Arnetminer: Expertise Oriented Search Using Social Networks, Frontiers of Computer Science in China, 2008, 1, Springer. (to appear)

l  Jing Zhang, Jie Tang, Liu Liu, and Juanzi Li. A Mixture Model for Expert Finding. In Proceedings of 2008 Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD’2008). pp. 466-478. [URL] [PDF] [Slides]

l  Jie Tang, Duo Zhang, Limin Yao, and Yi Li. Automatic Semantic Annotation using Machine Learning. In the book of The Semantic Web for Knowledge and Data Management: Technologies and Practices. Zhongmin Ma (Ed.), Springer Inc. (to appear)

l  Jie Tang, Bangyong Liang, and Juanzi Li. SWARMS: A Platform for Domain Knowledge Management and Applications. In the book of The Semantic Web for Knowledge and Data Management: Technologies and Practices. Zhongmin Ma (Ed.), Springer Inc. (to appear)

2007

l  Jie Tang, Jing Zhang, Duo Zhang, Limin Yao, and Chunlin Zhu. ArnetMiner: An Expertise Oriented Search System for Web Community. Semantic Web Challenge. In Proceedings of the 6th International Conference of Semantic Web (ISWC’2007).

l  Jie Tang