Interactive predicate suggestion for keyword search on RDF graphs

  • Authors:

  • Mengxia Jiang;Yueguo Chen;Jinchuan Chen;Xiaoyong Du

  • Affiliations:

  • School of Information, Renmin University of China, Beijing, China;Key Laboratory of Data Engineering and Knowledge Engineering, MOE, Renmin University of China, China;Key Laboratory of Data Engineering and Knowledge Engineering, MOE, Renmin University of China, China;School of Information, Renmin University of China, Beijing, China

  • Venue:
  • ADMA'11 Proceedings of the 7th international conference on Advanced Data Mining and Applications - Volume Part II
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

With the rapid growth of RDF data set, searching RDF data has recently received much attention. So far, structural languages such as SPARQL support to search RDF data efficiently and accurately. Unfortunately it requires users to have the prior knowledge of the underlying schema and query syntax of RDF data set. On the other hand, keyword search over graphs outperforms SPARQL queries in terms of usability. However, the predicate information is ignored in keyword queries, which results in the huge searching space and generates ambiguous interpretation of queries. In this paper, we design an interactive process of keyword search, which allows users to reduce the ambiguity of keywords by selecting some predicates to constrain the semantics of query keywords. We propose an efficient and effective algorithm to online discover a small number of predicates for users to choose. Experiments on the YAGO data set demonstrate the effectiveness and efficiency of our method.