A comparative study of neural machine translation models for Turkish language

Basit Öğe Kaydı
dc.authoridVelioglu, Riza/0000-0002-2160-4976
dc.contributor.authorOzdemir, Ozgur
dc.contributor.authorAkin, Emre Salih
dc.contributor.authorVelioglu, Riza
dc.contributor.authorDalyan, Tugba
dc.date.accessioned2024-07-18T20:49:19Z
dc.date.available2024-07-18T20:49:19Z
dc.date.issued2022
dc.departmentİstanbul Bilgi Üniversitesien_US
dc.description.abstractMachine translation (MT) is an important challenge in the fields of Computational Linguistics. In this study, we conducted neural machine translation (NMT) experiments on two different architectures. First, Sequence to Sequence (Seq2Seq) architecture along with a variation that utilizes attention mechanism is performed on translation task. Second, an architecture that is fully based on the self-attention mechanism, namely Transformer, is employed to perform a comprehensive comparison. Besides, the contribution of employing Byte Pair Encoding (BPE) and Gumbel Softmax distributions are examined for both architectures. The experiments are conducted on two different datasets: TED Talks that is one of the popular benchmark datasets for NMT especially among morphologically rich languages like Turkish and WMT18 News dataset that is provided by The Third Conference on Machine Translation (WMT) for shared tasks on various aspects of machine translation. The evaluation of Turkish-to-English translations' results demonstrate that the Transformer model with combination of BPE and Gumbel Softmax achieved 22.4 BLEU score on TED Talks and 38.7 BLUE score on WMT18 News dataset. The empirical results support that using Gumbel Softmax distribution improves the quality of translations for both architectures.en_US
dc.identifier.doi10.3233/JIFS-211453
dc.identifier.endpage2113en_US
dc.identifier.issn1064-1246
dc.identifier.issn1875-8967
dc.identifier.issue3en_US
dc.identifier.scopus2-s2.0-85124646682en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.startpage2103en_US
dc.identifier.urihttps://doi.org/10.3233/JIFS-211453
dc.identifier.urihttps://hdl.handle.net/11411/8170
dc.identifier.volume42en_US
dc.identifier.wosWOS:000752849700054en_US
dc.identifier.wosqualityQ4en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherIos Pressen_US
dc.relation.ispartofJournal of Intelligent & Fuzzy Systemsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectNeural Machine Translationen_US
dc.subjectGumbel Softmaxen_US
dc.subjectSequence To Sequenceen_US
dc.subjectTransformeren_US
dc.titleA comparative study of neural machine translation models for Turkish languageen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

Web of Science Indexed Publications
Scopus Indexed Publications