Exploiting semantic tags in XML retrieval

  • Authors:

  • Qiuyue Wang;Qiushi Li;Shan Wang;Xiaoyong Du

  • Affiliations:

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

  • Venue:
  • INEX'09 Proceedings of the Focused retrieval and evaluation, and 8th international conference on Initiative for the evaluation of XML retrieval
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

With the new semantically annotated Wikipedia XML corpus, we attempt to investigate the following two research questions. Do the structural constraints in CAS queries help in retrieving an XML document collection containing semantically rich tags? How to exploit the semantic tag information to improve the CO queries as most users prefer to express the simplest forms of queries? In this paper, we describe and analyze the work done on comparing CO and CAS queries over the document collection at INEX 2009 ad hoc track, and we propose a method to improve the effectiveness of CO queries by enriching the element content representations with semantic tags. Our results show that the approaches of enriching XML element representations with semantic tags are effective in improving the early precision, while on average precisions, strict interpretation of CAS queries are generally superior.