Semantic parallelism for documentary database systems

  • Nadejda Biscondi
5. Posters
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1401)


As data volume and query processing loads increase, companies that provide information retrieval services are turning to high performance parallel computing, storage and searching. In this paper we present a new paradigm of semantic parallelism dedicated to documentary databases. Based on existing parallel database techniques, our approach uses particular features of documentary databases to retrieve semantically relevant information in a more rapid and efficient way. Thus it can greatly alleviate both information overload and vocabulary problem of information retrieval. Extensive simulation results confirm the efficiency of our approach.


Parallel query processing parallel algorithms information retrieval semantic analysis 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    N.Biscondi, A.Flory, L.Brunie, H.Kosch: Encapsulation of Intra-Operator Parallelism in a Parallel Match Operator. Int. Conf. ACPC'96, Springer LNCS1127 (1996)Google Scholar
  2. 2.
    N.Biscondi: A New Parallel Computing Approach to Documentary Databases. Research Report RR98-1, INSA de Lyon, France (1998)Google Scholar
  3. 3.
    N.DeClaris, D.Harman, C.Faloutsos, S.Dumais, D.Oard: Information Filtering and Retrieval: Overview, Issues and Directions. Int. Conf. of the IEEE Engineering in Medicine and Biology Society, Baltimore, USA (1994)Google Scholar
  4. 4.
    W.Hasan, D.Florescu, P.Valduriez: Open Issues in Parallel Query Optimization. SIGMOD Record N3, vol.25 (1996)Google Scholar
  5. 5.
    A. Tomasic, H.Garcia-Molina: Performance of Inverted Indices in Shared-Nothing Distributed Text Document Information Retrieval System. Int. Conf. PDIS'93Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Nadejda Biscondi
    • 1
  1. 1.LISI, INSA de LyonVilleurbanneFrance

Personalised recommendations