Lindsey, Robert; Stipicevic, Michael; Veksler, Vladislav Daniel; Gray, Wayne D
BLOSSOM: Best path length on a semantic self-organizing map Incollection
Sloutsky, Vladimir ; Love, Brad ; McRae, Ken (Ed.): 30th Annual Meeting of the Cognitive Science Society, pp. 481-486, Cognitive Science Society, Austin, TX, 2008.
@incollection{lindsey08csc,
title = {BLOSSOM: Best path length on a semantic self-organizing map},
author = { Robert Lindsey and Michael Stipicevic and Vladislav Daniel Veksler and Wayne D. Gray},
editor = {Sloutsky, Vladimir and Love, Brad and McRae, Ken},
year = {2008},
date = {2008-01-01},
booktitle = {30th Annual Meeting of the Cognitive Science Society},
pages = {481-486},
publisher = {Cognitive Science Society},
address = {Austin, TX},
abstract = {We describe Vector Generation from Explicitly-defined Multidimensional semantic Space (VGEM), a method for converting a measure of semantic relatedness (MSR) into vector form. We also describe Best path Length on a Semantic Self-Organizing Map (BLOSSOM), a semantic relatedness technique employing VGEM and a connectionist, nonlinear dimensionality reduction technique. The psychological validity of BLOSSOM is evaluated using test cases from a large free-association norms dataset; we find that BLOSSOM consistently shows improvement over VGEM. BLOSSOM matches the performance of its base-MSR using a 21 dimensional vector-space and shows promise to outperform its base-MSR with a more rigorous exploration of the parameter space. In addition, BLOSSOM provides benefits such as document relatedness, concept-path formation, intuitive visualizations, and unsupervised text clustering.},
keywords = {BLOSSOM, computational linguistics, Dijkstra's algorithm, Measures of Semantic Relatedness, natural language processing, nonlinear dimensionality reduction, Self- Organizing Maps, SOM traversal, VGEM},
pubstate = {published},
tppubtype = {incollection}
}
We describe Vector Generation from Explicitly-defined Multidimensional semantic Space (VGEM), a method for converting a measure of semantic relatedness (MSR) into vector form. We also describe Best path Length on a Semantic Self-Organizing Map (BLOSSOM), a semantic relatedness technique employing VGEM and a connectionist, nonlinear dimensionality reduction technique. The psychological validity of BLOSSOM is evaluated using test cases from a large free-association norms dataset; we find that BLOSSOM consistently shows improvement over VGEM. BLOSSOM matches the performance of its base-MSR using a 21 dimensional vector-space and shows promise to outperform its base-MSR with a more rigorous exploration of the parameter space. In addition, BLOSSOM provides benefits such as document relatedness, concept-path formation, intuitive visualizations, and unsupervised text clustering.