A1 Journal article (refereed)
Graph-based exploration and clustering analysis of semantic spaces (2019)

Veremyev, A., Semenov, A., Pasiliao, E. L., & Boginski, V. (2019). Graph-based exploration and clustering analysis of semantic spaces. Applied Network Science, 4, Article 104. https://doi.org/10.1007/s41109-019-0228-y

JYU authors or editors

Publication details

All authors or editors: Veremyev, Alexander; Semenov, Alexander; Pasiliao, Eduardo L.; Boginski, Vladimir

Journal or series: Applied Network Science

eISSN: 2364-8228

Publication year: 2019

Volume: 4

Article number: 104

Publisher: SpringerOpen

Publication country: Germany

Publication language: English

DOI: https://doi.org/10.1007/s41109-019-0228-y

Publication open access: Openly available

Publication channel open access: Open Access channel

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/67708

Abstract

The goal of this study is to demonstrate how network science and graph theory tools and concepts can be effectively used for exploring and comparing semantic spaces of word embeddings and lexical databases. Specifically, we construct semantic networks based on word2vec representation of words, which is “learnt” from large text corpora (Google news, Amazon reviews), and “human built” word networks derived from the well-known lexical databases: WordNet and Moby Thesaurus. We compare “global” (e.g., degrees, distances, clustering coefficients) and “local” (e.g., most central nodes and community-type dense clusters) characteristics of considered networks. Our observations suggest that human built networks possess more intuitive global connectivity patterns, whereas local characteristics (in particular, dense clusters) of the machine built networks provide much richer information on the contextual usage and perceived meanings of words, which reveals interesting structural differences between human built and machine built semantic networks. To our knowledge, this is the first study that uses graph theory and network science in the considered context; therefore, we also provide interesting examples and discuss potential research directions that may motivate further research on the synthesis of lexicographic and machine learning based tools and lead to new insights in this area.

Keywords: network theory; semantic web

Free keywords: semantic spaces; graph theory; word2vec similarity networks; cohesive clusters; cliques; clique relaxations

Contributing organizations

Related projects

Ministry reporting: Yes

VIRTA submission year: 2019

JUFO rating: 1