A fuzzy model for NMT word alignment using quasi-perfect matching

Basit Öğe Kaydı
dc.authoridKhalili, Majid/0000-0003-0207-505X
dc.authorwosidBorzooei, Rajab Ali/AAE-8211-2021
dc.authorwosidKhalili, Majid/AAO-2220-2021
dc.contributor.authorKhalili, M.
dc.contributor.authorBorzooei, R. A.
dc.contributor.authorEbrahimibagha, D.
dc.date.accessioned2024-05-19T14:40:22Z
dc.date.available2024-05-19T14:40:22Z
dc.date.issued2023
dc.departmentİstinye Üniversitesien_US
dc.description.abstractIn this article, first, the concept of quasi-perfect matching in a fuzzy graph is introduced. In addition to using these types of matching in expressing our main application goal, this introduction provides a complete classification on all matching that are known as maximum matching in classical graph theory. A useful set called conductive set has been obtained to be able to customize any of the introduced categories for matchings as desired or according to the practical necessity. Extensions with different powers are made from a fuzzy graph and useful meters are generated on each of them. These extensions and related concepts have been used in a different approach for words alignment in machine translation. The mismatch between the number of sentence words in the source and target languages has always been a challenge for the designers of machine translation systems in word-based alignment. To solve this, we introduce a different approach for aligning words, based on a fuzzy graph extracted from a parallel corpus.en_US
dc.identifier.doi10.1007/s40314-023-02498-1
dc.identifier.issn2238-3603
dc.identifier.issn1807-0302
dc.identifier.issue8en_US
dc.identifier.scopus2-s2.0-85178226513en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.urihttps://doi.org10.1007/s40314-023-02498-1
dc.identifier.urihttps://hdl.handle.net/20.500.12713/4950
dc.identifier.volume42en_US
dc.identifier.wosWOS:001110665800002en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringer Heidelbergen_US
dc.relation.ispartofComputational & Applied Mathematicsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmz20240519_kaen_US
dc.subjectConductive Seten_US
dc.subjectWords Alignmenten_US
dc.subjectQuasi-Perfect Matchingen_US
dc.subjectSelf-Perfect Matchingen_US
dc.titleA fuzzy model for NMT word alignment using quasi-perfect matchingen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu