Large-scale evaluation of dependency-based DSMs: Are they worth the effort?
Gabriella Lapesa, Stefan Evert · 2017
This paper presents a large-scale evaluation study of dependency-based distributional semantic models.We evaluate dependencyfiltered and dependency-structured DSMs in a number of standard semantic similarity tasks, systematically exploring their parameter space in order to give them a "fair shot" against window-based models.Our results show that properly tuned window-based DSMs still outperform the dependencybased models in most tasks.There appears to be little need for the language-dependent resources and computational cost associated with syntactic analysis.1