On the Specification of Term Values in Automatic Indexing

By Gerard A. Salton, C. S. Yang. 1973

Subfields: Information Retrieval & Search

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Retrieval & Search

Citations in the corpus

Unfolding Physiological State: Mortality Modelling in Intensive Care Units (2014, methodology): “A TF-IDF metric [14] was applied to determine the 500 most informative words in each patient’s notes, and we then limited our overall vocabulary to the union of the most informative words per-patient.”
A vector space model for automatic indexing (1975, methodology): “The indexing theory which consists in using certain elements extracted from document texts directly as index terms, combined with phrases made up of high frequency components and thesaurus classes defined from low frequency elements has been tested using document collections in aerodynamics (CRAN”
Information Retrieval Evaluation (2011, methodology): “This initial set of test collections was heavily used, particularly the Cranfield424, TIME, and MED450 set (for example, see [144]).”
Term-Weighting Approaches in Automatic Text Retrieval (1988, methodology): “A reasonable measure of term importance may then be obtained by using the product of the term frequency and the inverse document frequency (tf x idf) [39-411.”
LIBLINEAR: A Library for Large Linear Classification (2008, background): “TF-IDF (term frequency, inverse document frequency); see Salton and Yang (1973) and any information retrieval book.”
Understanding inverse document frequency: on theoretical arguments for IDF (2004, methodology): “TF*IDF-style measures emerged from extensive empirical studies of combinations of weighting factors, particularly by the Cornell group (Salton and Yang, 1973).”