Word Representation: Theoretical Explanation of an Empirical Fact

Authors

Leonel Escapita, The University of Texas at El PasoFollow
Diana Licon, The University of Texas at El PasoFollow
Madison Anderson, The University of Texas at El PasoFollow
Diego Pedraza, The University of Texas at El PasoFollow
Vladik Kreinovich, The University of Texas at El PasoFollow

Publication Date

11-1-2022

Comments

Technical Report: UTEP-CS-22-110

Abstract

There is a reasonably accurate empirical formula that predicts, for two words i and j, the number Xij of times when the word i will appear in the vicinity of the word j. The parameters of this formula are determined by using the weighted least square approach. Empirically, the predictions are the most accurate if we use the weights proportional to a power of Xij. In this paper, we provide a theoretical explanation for this empirical fact.