A complex network approach to semantic spaces: How meaning organizes itself

We propose a complex network approach to the emergence of word meaning through the analysis of semantic spaces: NLP techniques able to capture an aspect of meaning based on distributional semantic theories, so that words are linked to each other if they can be substituted in the same linguistic contexts, forming clusters representing semantic fields. This approach can be used to model a mental lexicon of word similarities: a graph G = (N, L) where N are words connected by some type of semantic or associative property L. Networks extracted from a baseline neural language model are analyzed in terms of global properties: they are small world and the probability of degree distribution follows a truncated power law. Moreover, they throw in a strong degree assortativity, a peculiarity that introduces us to the problem of semantic field identification. We support the idea that semantic fields can be identified exploiting the topological information of networks. Several community discovery methods have been tested, identifying from time to time strict semantic fields as crisp communities, linguistic contexts as overlapping communities or meaning conveyed by single words as communities produced starting from a seed-set expansion.