Probabilistic Information Retrieval as Combination of Abstraction, Inductive Learning and Probabilistic Assumptions

  • Zitationsschlüssel:
    Fuhr/Pfeifer:94
  • Titel:
    Probabilistic Information Retrieval as Combination of Abstraction, Inductive Learning and Probabilistic Assumptions
  • Autor(en):
    N. Fuhr
    U. Pfeifer
  • Journal:
    ACM Transactions on Information Systems
  • Ausgabe:
    12
  • Nummer:
    1
  • Seite(n):
    92--115
  • Jahr:
    1994

Zusammenfassung:


We show that former approaches in probabilistic information retrieval are based on one or two of the three concepts abstraction, inductive learning and probabilistic assumptions, and we propose a new approach which combines all three concepts. This approach is illustrated for the case of indexing with a controlled vocabulary. For this purpose, we describe a new probabilistic model first, which is then combined with logistic regression, thus yielding a generalization of the original model. Experimental results for the pure theoretical model as well as for heuristic variants are given. Furthermore, linear and logistic regression are compared.
Klassifikation(en):
H.3.3
Subjektdeskriptor(en):
retrieval models
Schlüsselwörter:
probabilistic retrieval

Volltext als PS