Show simple item record

dc.contributor.authorVeremyev, Alexander
dc.contributor.authorSemenov, Alexander
dc.contributor.authorPasiliao, Eduardo L.
dc.contributor.authorBoginski, Vladimir
dc.date.accessioned2020-02-04T07:33:39Z
dc.date.available2020-02-04T07:33:39Z
dc.date.issued2019
dc.identifier.citationVeremyev, A., Semenov, A., Pasiliao, E. L., & Boginski, V. (2019). Graph-based exploration and clustering analysis of semantic spaces. <i>Applied Network Science</i>, <i>4</i>, Article 104. <a href="https://doi.org/10.1007/s41109-019-0228-y" target="_blank">https://doi.org/10.1007/s41109-019-0228-y</a>
dc.identifier.otherCONVID_33552915
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/67708
dc.description.abstractThe 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.en
dc.format.mimetypeapplication/pdf
dc.languageeng
dc.language.isoeng
dc.publisherSpringerOpen
dc.relation.ispartofseriesApplied Network Science
dc.rightsCC BY 4.0
dc.subject.othersemantic spaces
dc.subject.othergraph theory
dc.subject.otherword2vec similarity networks
dc.subject.othercohesive clusters
dc.subject.othercliques
dc.subject.otherclique relaxations
dc.titleGraph-based exploration and clustering analysis of semantic spaces
dc.typearticle
dc.identifier.urnURN:NBN:fi:jyu-202002041965
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.contributor.oppiaineTietojärjestelmätiedefi
dc.contributor.oppiaineInformation Systems Scienceen
dc.type.urihttp://purl.org/eprint/type/JournalArticle
dc.description.reviewstatuspeerReviewed
dc.relation.issn2364-8228
dc.relation.volume4
dc.type.versionpublishedVersion
dc.rights.copyright© The Authors, 2019
dc.rights.accesslevelopenAccessfi
dc.relation.grantnumberFA9550-17-1-0030
dc.subject.ysosemanttinen web
dc.subject.ysoverkkoteoria
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p21716
jyx.subject.urihttp://www.yso.fi/onto/yso/p2543
dc.rights.urlhttps://creativecommons.org/licenses/by/4.0/
dc.relation.doi10.1007/s41109-019-0228-y
dc.relation.funderAir Force Office of Scientific Researchfi
dc.relation.funderAir Force Office of Scientific Researchen
jyx.fundingprogramMuutfi
jyx.fundingprogramOthersen
jyx.fundinginformationThe work of V. Boginski and A. Veremyev was supported in part by the U.S. Air Force Research Laboratory (AFRL) award FA8651-16-2-0009. The work of A. Semenov was supported in part by the U.S. Air Force Research Laboratory (AFRL) European Office of Aerospace Research and Development under Grant FA9550-17-1-0030.


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

CC BY 4.0
Except where otherwise noted, this item's license is described as CC BY 4.0