Si-SEEKER: ontology-based semantic search over databases

  • Authors:

  • Jun Zhang;Zhaohui Peng;Shan Wang;Huijing Nie

  • Affiliations:

  • School of Information, Renmin University of China, Beijing, P.R. China;School of Information, Renmin University of China, Beijing, P.R. China;School of Information, Renmin University of China, Beijing, P.R. China;School of Information, Renmin University of China, Beijing, P.R. China

  • Venue:
  • KSEM'06 Proceedings of the First international conference on Knowledge Science, Engineering and Management
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

Keyword Search Over Relational Databases(KSORD) has been widely studied. While keyword search is helpful to access databases, it has inherent limitations. Keyword search doesn’t exploit the semantic relationships between keywords such as hyponymy, meronymy and antonymy, so the recall rate and precision rate are often dissatisfactory. In this paper, we have designed an ontology-based semantic search engine over databases called Si-SEEKER based on our i-SEEKER system which is a KSORD system with our candidate network selection techniques. Si-SEEKER extends i-SEEKER with semantic search by exploiting hierarchical structure of domain ontology and a generalized vector space model to compute semantic similarity between a user query and annotated data. We combine semantic search with keyword search over databases to improve the recall rate and precision rate of the KSORD system. We experimentally evaluate our Si-SEEKER system on the DBLP data set and show that Si-SEEKER is more effective than i-SEEKER in terms of the recall rate and precision rate of retrieval results.