A novel embedding approach to learn word vectors by weighting semantic relations: SemSpace

Basit Öğe Kaydı
dc.authoridOrhan, Umut/0000-0003-1882-6567
dc.authoridTulu, Cagatay Neftali/0000-0002-4462-3707
dc.contributor.authorOrhan, Umut
dc.contributor.authorTulu, Cagatay Neftali
dc.date.accessioned2025-01-06T17:44:20Z
dc.date.available2025-01-06T17:44:20Z
dc.date.issued2021
dc.description.abstractIn this study, we propose a novel embedding approach, called as SemSpace, to determine word vectors of synsets and to find the best weights for semantic relations. First, SemSpace finds the optimum weights to the semantic relations in WordNet by aligning them to values produced by human intelligence, and then, determines word vectors of synsets by adjusting euclidean distances among them. Proposed approach requires two inputs; first, a lexical-semantic network such as WordNet, second, a word-level similarity dataset generated by people. In the experiments, we used WordNet 3.0 data for the lexical-semantic network, and three (RG65, WS353, and MEN3K) benchmark testsets to align semantic weights. Using the aligned semantic weights and the determined word vectors, the obtained resultsresults on the benchmark testsets are compared with literature studies. According to the obtained results, it might be concluded that SemSpace is not only successful to find word level semantic similarity values and semantic weights, but also to discover new semantic relations with their semantic levels.
dc.identifier.doi10.1016/j.eswa.2021.115146
dc.identifier.issn0957-4174
dc.identifier.issn1873-6793
dc.identifier.scopus2-s2.0-85105604279
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1016/j.eswa.2021.115146
dc.identifier.urihttps://hdl.handle.net/20.500.14669/3005
dc.identifier.volume180
dc.identifier.wosWOS:000732710500004
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherPergamon-Elsevier Science Ltd
dc.relation.ispartofExpert Systems With Applications
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_20241211
dc.subjectSemSpace
dc.subjectEmbedding
dc.subjectWord vectors
dc.subjectAligning semantic relations to weights
dc.subjectWordNet
dc.titleA novel embedding approach to learn word vectors by weighting semantic relations: SemSpace
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu