Evaluating the psychological plausibility of word2vec and GloVe distributional semantic models

Tech Report, 2018

Ivana Kajić, Chris Eliasmith

Abstract

The representation of semantic knowledge poses a central modelling decision in many models of cognitive phenomena. However, not all such representations reflect properties observed in human semantic networks. Here, we evaluate the psychological plausibility of two distributional semantic models widely used in natural language processing: word2vec and GloVe. We use these models to construct directed and undirected semantic networks and compare them to networks of human association norms using a set of graph-theoretic analyses. Our results show that all such networks display small-world characteristics, while only undirected networks show similar degree distributions to those in the human semantic network. Directed networks also exhibit a hierarchical organization that is reminiscent of the human semantic network.

Full text links

PDF

External link

CTN Tech Report

Issn
CTN-TR-20180824-012
Address
Waterloo, ON
Month
08
Doi
10.13140/RG.2.2.25289.60004
Institution
Centre for Theoretical Neuroscience

Cite

Plain text

BibTeX