The Discriminative Lexicon: A Unified Computational Model for the Lexicon and Lexical Processing in Comprehension and Production Grounded Not in (De)Composition but in Linear Discriminative Learning

Table 2

Summary of a Gaussian location scale additive model fitted to the similarity ratings in the MEN dataset, with as predictor the correlation of word’s semantic vectors in the matrix. TPRS: thin plate regression spline. b: the minimum standard deviation for the logb link function. Location: parameter estimating the mean; scale: parameter estimating the variance through the logb link function ().

A. parametric coefficients	Estimate	Std. Error	t-value	p-value
Intercept [location]	25.2990	0.1799	140.6127	0.0001
Intercept [scale]	2.1297	0.0149	143.0299	0.0001
B. smooth terms	edf	Ref.df	F-value	p-value
TPRS [location]	8.3749	8.8869	2766.2399	0.0001
TPRS [scale]	5.9333	7.0476	87.5384	0.0001