T
Taner Uçkan
Researcher at Yüzüncü Yıl University
Publications - 14
Citations - 85
Taner Uçkan is an academic researcher from Yüzüncü Yıl University. The author has contributed to research in topics: Automatic summarization & Jaccard index. The author has an hindex of 4, co-authored 12 publications receiving 43 citations.
Papers
More filters
Journal ArticleDOI
Extractive multi-document text summarization based on graph independent sets
Taner Uçkan,Ali Karci +1 more
TL;DR: The Maximum Independent Set, which has not been used previously in any summarization study, has been utilized within the context of this study and a text processing tool is suggested in order to preserve the semantic cohesion between sentences in the representation stage of introductory texts.
Proceedings ArticleDOI
Applications and Comparisons of Optimization Algorithms Used in Convolutional Neural Networks
TL;DR: In this study, Convolutional Neural Network (CNN) model from the Deep Learning Algorithms and the Optimization Algorithm used in Deep Learning have been applied to international image data sets.
Proceedings ArticleDOI
Extractive Text Summarization via Graph Entropy Çizge Entropi ile Çıkarıcı Metin Özetleme
TL;DR: A subtractive, general and unsupervised summarization system is provided to represent the texts to be summarized with graphs and then graph entropy is used to interpret the structural stability and structural information content on the graphs representing the text files.
Journal Article
Fidan Gelişim ve Lig Şampiyonluk Algoritmaları Kullanarak Aşırı-Akım Rölelerin Optimum Koordinasyonu
TL;DR: Gerekli uyarlama ve kodlamalar .NET platformu kullanilarak gerceklestirilmis ve asiri-akim role koordinasyon degerlerinde oldukca iyi sayilabilecek sonuclara ulasilmistir.
Proceedings ArticleDOI
Doğal dil İşleme yaklaşimlari ile yapisal olmayan dökümanlarin benzerliği
Cengiz Hark,Adilcevaz Myo,Abubekir Seyyarer,Gevas Myo,Taner Uçkan,Baskale Myo,Ali Karci,Bilgisayar Muhendisligi +7 more
TL;DR: The R programming language labels have been used to structure only text based documents stacks in order to make them proccessable and to determine their similiraties afterwards.