CORDER is supported by the Dot.Kom project, Stela Institute and the AKT project.
Team:Dr. Jianhan Zhu
Alexandre L. Goncalves
Dr. Victoria Uren
Prof. Enrico Motta
Prof. Roberto Pacheco
Related Projects:
ESpotter
System Description:
CORDER (COmmunity Relation Discovery by named Entity Recognition) is an un-supervised machine learning algorithm that exploits named entity recognition and co-occurrence data to associate individuals in a community with their expertise and associates. CORDER discovers relations from the Web pages of the community. Its approach is based on co-occurrences of NEs and the distances between them. For a given NE, there are a number of co-occurring NEs. We assume that NEs that are closely related to each other tend to appear together more often and closer to each other in Web pages. We calculate a relation strength for each co-occurring NE based on its co-occurrences and distances from the given NE. The co-occurring NEs are ranked by their relation strengths.
System Architecture:
Demos:
Try the Demo here
Papers:
Jianhan Zhu, Marc Eisenstadt, Alexandre L. Gonçalves, Chris Denham, Victoria S. Uren, Enrico Motta, Roberto Pacheco. BuddyFinder-CORDER: Online Social Networking by Community Relation Discovery. To appear in Proc. of International Semantic Web Conference (ISWC2005) Workshop on Semantic Network Analysis, November 7, 2005, Galway, Ireland.
Jianhan Zhu, Alexandre L. Gonçalves, Victoria S.Uren, Enrico Motta, Roberto Pacheco. Mining Web Data for Competency Management. To appear in Proc. of Web Intelligence 2005 (WI'2005), France, September 19-22, 2005.
Jianhan Zhu, Alexandre L. Gonçalves, Victoria S.Uren, Enrico Motta, Roberto Pacheco. CORDER: COmmunity Relation Discovery by named Entity Recognition. Poster to appear in Proc. of Third International Conference on Knowledge Capture (K-Cap'2005), October 2-5, 2005 Banff, Canada.
 |
 |