Term-Weighting Approaches in Automatic Text Retrieval

By Gerard A. Salton, Chris Buckley. 1988

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

From Frequency to Meaning: Vector Space Models of Semantics (2010, background): “Salton and Buckley (1988) defined a large family of tf-idf weighting functions and evaluated them on information retrieval tasks, demonstrating that tf-idf weighting can yield significant improvements over raw frequency.”
Compressing Neural Networks with the Hashing Trick (2015, methodology): “…the hashing trick ) (Wein-berger et al., 2009; Shi et al., 2009) is a technique to map high-dimensional text documents directly into bag-of-word (Salton & Buckley, 1988) vectors, which would otherwise require use of memory consuming dictionaries for storage of indices corresponding with speciﬁc…”
Marginalized Denoising Autoencoders for Domain Adaptation (2012, methodology): “To be fair to other algorithms that we compare to, we also pre-process with tf-idf (Salton & Buckley, 1988) and use the transformed feature vectors as their input if that leads to better results.”
A Survey on Dialogue Systems: Recent Advances and New Frontiers (2017, background): “[114] incorporated inverse document frequency (IDF) [65] into the training process to measure the response diversity.”
When does a compliment become sexist? Analysis and classification of ambivalent sexism using twitter data (2017, methodology): “We ensure that SVM uses TF-IDF, to construct a separating hyperplane for given labelled training data and classify new tweets into one of the three classes: ‘Benevolent’, ‘Hostile’, or ‘Others’.”
LIM-LIG at SemEval-2017 Task1: Enhancing the Semantic Similarity for Arabic Sentences with Vectors Weighting (2017, methodology): “In this variant, the Inverse Document Frequency IDF concept is used to produce a composite weight for each word in each sentence.”
Why batch and user evaluations do not give the same results (2001, background): “A common view held by many information retrieval (IR) researchers is that “batch” retrieval evaluations are reliable in determining the efficacy of one retrieval system versus another [1].”
Information filtering and information retrieval: two sides of the same coin? (1992, background): “In the vector-space model, term weights can be interpreted as probability estimates [31] and a great deal of experimental work has been done to evaluate alternative forms [19].”
Probabilistic models of information retrieval based on measuring the divergence from randomness (2002, methodology): “Kwok reported that the ICTF performed much better than Salton s IDF model [Salton and Buckley 1988].”
Information diffusion in online social networks: a survey (2013, methodology): “To this end, they develop a five-step process that firstly formalize the messages content as vectors of terms with their relative frequencies computed by using the augmented normalized term frequency [43].”