Image Captioning in Turkish Language

dc.authoridYildiz, Tugba/0000-0002-8552-2806|Battini Sonmez, Elena/0000-0003-0090-984X
dc.authorwosidYildiz, Tugba/ABC-5958-2020
dc.authorwosidBattini Sonmez, Elena/AAZ-6358-2021
dc.contributor.authorYilmaz, Berk Dursun
dc.contributor.authorDemir, Ali Emre
dc.contributor.authorSonmez, Elena Battini
dc.contributor.authorYildiz, Tugba
dc.date.accessioned2024-07-18T20:47:19Z
dc.date.available2024-07-18T20:47:19Z
dc.date.issued2019
dc.departmentİstanbul Bilgi Üniversitesien_US
dc.descriptionInnovations in Intelligent Systems and Applications Conference (ASYU) -- OCT 31-NOV 02, 2019 -- Izmir, TURKEYen_US
dc.description.abstractImage captioning is one of the everlasting challenging tasks in the field of artificial intelligence that requires computer vision and natural language processing. Plenty of salient works have been proposed throughout the time for English language however, the number of studies in Turkish language is still too limited. This paper couples an encoder CNN-the component that is responsible for extracting the features of the given images-, with a decoder RNN -the component that is responsible for generating captions using the given inputs-to generate Turkish captions within human gold-standards. We conducted the experiments using the most common evaluation metrics such as BLEU, METEOR, ROUGE and CIDEr. Results show that the performance of the proposed model is satisfactory in both qualitative and quantitatively evaluations. A Web App is already deployed to allow volunteers to contribute to the improvements of the Turkish captioned dataset.en_US
dc.description.sponsorshipYasar Univ,IEEE Turkey Sect,Yildiz Teknik Univ,Idea,Siemensen_US
dc.identifier.doi10.1109/asyu48272.2019.8946358
dc.identifier.endpage417en_US
dc.identifier.isbn978-1-7281-2868-9
dc.identifier.scopus2-s2.0-85078328283en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.startpage413en_US
dc.identifier.urihttps://doi.org/10.1109/asyu48272.2019.8946358
dc.identifier.urihttps://hdl.handle.net/11411/7770
dc.identifier.wosWOS:000631252400077en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.relation.ispartof2019 Innovations in Intelligent Systems and Applications Conference (Asyu)en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectTurkish İmage Captioningen_US
dc.subjectComputer Visionen_US
dc.subjectNatural Language Processingen_US
dc.subjectMachine Learningen_US
dc.subjectDeep Neural Networksen_US
dc.subjectCnnen_US
dc.subjectRnnen_US
dc.titleImage Captioning in Turkish Languageen_US
dc.typeConference Objecten_US

Dosyalar