Advanced Generative AI Methods for Academic Text Summarization

Basit Öğe Kaydı
dc.authorscopusidAlaa Ali Hameed / 56338374100
dc.authorwosidAlaa Ali Hameed / ABI-8417-2020
dc.contributor.authorDar, Zaema
dc.contributor.authorRaheel, Muhammad
dc.contributor.authorBokhari, Usman
dc.contributor.authorJamil, Akhtar
dc.contributor.authorAlazawi, Esraa Mohammed
dc.contributor.authorHameed, Alaa Ali
dc.date.accessioned2025-04-18T09:50:19Z
dc.date.available2025-04-18T09:50:19Z
dc.date.issued2024
dc.departmentİstinye Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.description.abstractThe exponential growth of scientific literature emphasizes the need for employing advanced techniques for effective text summarization, which can significantly speed up the research process. This study tackles the challenge by advancing scientific text summarization through AI and deep learning methods. We delve into the integration and fine-tuning of cutting-edge models, including LED-Large, Pegasus variants, and BART, aiming to refine the summarization process. Unique combinations, such as SciBERT with LED-Large, were investigated to ensure the capture of critical details frequently missed by traditional methods. This novel approach led to notable improvements in summarization effectiveness. Our findings indicate that models like LED-Large excel in quickly adapting to training data, achieving impressive semantic understanding with fewer training epochs, evidenced by achieving a FRES score of 28.5852 and ROUGE scores, including a ROUGE-l F1-Score of 0.4991. However, while extensively trained models like BART -large and Pegasus displayed strong semantic capabilities, they also pointed to the necessity for refinements in readability and higher-order n-gram overlap in the produced summaries. © 2024 IEEE.
dc.identifier.citationDar, Z., Raheel, M., Bokhari, U., Jamil, A., Alazawi, E. M., & Hameed, A. A. (2024, April). Advanced Generative AI Methods for Academic Text Summarization. In 2024 IEEE 3rd International Conference on Computing and Machine Intelligence (ICMI) (pp. 1-7). IEEE.
dc.identifier.doi10.1109/ICMI60790.2024.10585622
dc.identifier.isbn979-835037297-7
dc.identifier.scopus2-s2.0-85199462633
dc.identifier.urihttps://hdl.handle.net/20.500.12713/6878
dc.identifier.wosWOS:001282083300002
dc.indekslendigikaynakScopus
dc.indekslendigikaynakWeb of Science
dc.institutionauthorHameed, Alaa Ali
dc.institutionauthoridAlaa Ali Hameed / 0000-0002-8514-9255
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartof2024 IEEE 3rd International Conference on Computing and Machine Intelligence, ICMI 2024 - Proceedings
dc.relation.publicationcategoryDiğer
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectBART
dc.subjectCosine Similarity
dc.subjectDeep Learning
dc.subjectLED-Large
dc.subjectLiterature Review Generation
dc.subjectNatural Language Processing
dc.subjectPegasus-Large
dc.subjectSciBERT
dc.subjectScientific Summarization
dc.subjectTransformers
dc.titleAdvanced Generative AI Methods for Academic Text Summarization
dc.typeConference Object

Dosyalar

Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Bilgisayar Mühendisliği Bölümü Bildiri Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu