Cross-language hybrid keyword and semantic search

  • Authors:
  • David W. Embley;Stephen W. Liddle;Deryle W. Lonsdale;Joseph S. Park;Byung-Joo Shin;Andrew J. Zitzelberger

  • Affiliations:
  • Department of Computer Science, Brigham Young University, Provo, Utah;Information Systems Department, Brigham Young University, Provo, Utah;Department of Linguistics and English Language, Brigham Young University, Provo, Utah;Department of Computer Science, Brigham Young University, Provo, Utah;Department of Computer Science & Engineering, Kyungnam University, Kyungnam, Korea;Department of Computer Science, Brigham Young University, Provo, Utah

  • Venue:
  • ER'12 Proceedings of the 31st international conference on Conceptual Modeling
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

The growth of multilingual web content and increasing internationalization portends the need for cross-language information retrieval. As a solution to this problem for narrow-domain, data-rich web content, we offer ML-HyKSS: MultiLingual Hybrid Keyword and Semantic Search. The primary component of ML-HyKSS is a collection of linguistically grounded conceptual-model instances called extraction ontologies. Extraction ontologies can recognize keywords and applicable semantics; when coupled with cross-language mappings at the conceptual level, they enable cross-language information retrieval and query processing. Our experimental results are promising, yielding good results for cross-language information retrieval with contrasting languages, application content, and cultures.