Generating headlines for Turkish news texts with transformer architecture based deep learning method

Basit Öğe Kaydı
dc.authoridKARACA, ABDULKADIR/0000-0003-1737-5944
dc.authorwosidKARACA, ABDULKADIR/JQV-8786-2023
dc.contributor.authorKaraca, Abdulkadir
dc.contributor.authorAydin, Ozlem
dc.date.accessioned2024-06-12T11:16:46Z
dc.date.available2024-06-12T11:16:46Z
dc.date.issued2024
dc.departmentTrakya Üniversitesien_US
dc.description.abstractNowadays, the Internet is a structure that people can access easily and at the same time produce content easily and without control. In parallel with this situation, the ability of extract information from the raw data that makes up big data has become more complex. The fact that the headlines of the contents contain uncontrolled and misleading elements makes it difficult to reach the right information. The headlines of the contents are important for people to reach the information they want in their limited time. In this study, it is aimed to produce headlines suitable for the content instead of headlines that may be misleading for news. For this purpose, an application that produces headlines for Turkish news with deep learning method has been developed. SuDer news corpus is used as dataset. For the training of the model, it is aimed to obtain more humanoid results in the production of news headlines by using the Transformer architecture, which is frequently preferred in natural language studies today and the abstract summarization method. In this study, in order to compare the performance of the Transformer model, models are prepared and trained with Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures. At the end of 25 epochs of training with LSTM, GRU and Transformer architectures on the corpus, the values of loss are 1.03, 0.55 and 2.49 respectively. In the experiments performed on the validation data, measurements are made with ROUGE-1, ROUGE-2 and ROUGE-L metrics. As a result of the measurements, it is observed that the Transformer architecture is partially good, based on the metric values produced. In addition, when the headlines produced with these architectures are examined, it is observed that the headline obtained with the Transformer architecture produce headlines that are partially more suitable for the news content compared to other architectures.en_US
dc.identifier.doi10.17341/gazimmfd.963240
dc.identifier.endpage495en_US
dc.identifier.issn1300-1884
dc.identifier.issn1304-4915
dc.identifier.issue1en_US
dc.identifier.scopus2-s2.0-85174494684en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.startpage485en_US
dc.identifier.urihttps://doi.org/10.17341/gazimmfd.963240
dc.identifier.urihttps://hdl.handle.net/20.500.14551/24451
dc.identifier.volume39en_US
dc.identifier.wosWOS:001058089000037en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherGazi Univ, Fac Engineering Architectureen_US
dc.relation.ispartofJournal Of The Faculty Of Engineering And Architecture Of Gazi Universityen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectTurkish Natural Language Processingen_US
dc.subjectAutomatic Headline Generationen_US
dc.subjectAbstract Text Summarizationen_US
dc.subjectDeep Learningen_US
dc.subjectTransformersen_US
dc.titleGenerating headlines for Turkish news texts with transformer architecture based deep learning methoden_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu