A Markovian random field approach to information retrieval

  title={A Markovian random field approach to information retrieval},
  author={Djamel Bouchaffra and Jean Guy Meunier},
  journal={Proceedings of 3rd International Conference on Document Analysis and Recognition},
  pages={997-1002 vol.2}
A Markovian random field approach is proposed for automatic information retrieval in full text documents. We draw up an analogy between a flow of queries/document images connections and statistical mechanics systems. The Markovian flow process machine (MFP) models the interaction between queries and document images as a dynamical system. The MFP machine searches to fit the user's queries by changing the set of descriptors contained in the document images. There is hence a constant… CONTINUE READING

Figures and Topics from this paper.


Publications referenced by this paper.

Analyse automatique du discours: Note sur le systkme 3AD75", Communication interne

J. Rouault
  • Universitk Stendhal, Grenoble,
  • 1994

Automatic 'structuring and retrieval of large texte file

J. Allan, C. Buckley
  • Communications of the ACM,
  • 1994

A model of cluster searching based on classification

W. B. Croft
  • Information Systems,
  • 1980