Filters

2013 - 201922020 - 20231
Reset filters

Settings

Department: Atılım UniversitySubject: Turkish

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Article
    Can Computers Read a Text With Stress?
    (Ahmet Yesevi Univ, 2013) Uslu, I. Baran; Demir, Nurettin; Ilk, H. Gokhan; Yilmaz, A. Egemen; Department of Electrical & Electronics Engineering
    Today prosodic elements such as stress, intonation and melody can be examined through computer-assisted techniques. The identification and analysis of acoustic qualities provide significant clues as to the suprasegmental aspects of speech. In this study a system was designed to enable speech synthesis using a Turkish text. This synthesizer was used to analyze the melodic sructures of selected sentences. Any speech synthesized by a computer needs to be equipped with a melodic model so that it will sound natural to the ear. Within the context of this study a melodic model was also suggested, and the elements of this model were analyzed and discussed in terms of the rules of linguistics.
  • Thumbnail Image
    Conference Object
    Citation - Scopus: 1
    Extractive Text Summarization for Turkish: Implementation of Tf-Idf and Pagerank Algorithms
    (Springer Science and Business Media Deutschland GmbH, 2023) Akülker,E.; Turhan,Ç.
    Due to the massive amount of information available on the web, reaching the desired content has become more and more difficult. Automatic text summarization helps to solve the problem by minimizing the document size while keeping its core information. In this study, two extractive single document automatic text summarization systems for Turkish are presented which implement the statistical-based TF-IDF algorithm as well as the combination of TF-IDF with the graph-based PageRank algorithm. The study aims to reveal the usability and effectiveness of these algorithms for Turkish documents. Moreover, the results of the TF-IDF implementation and the hybrid approach are compared using the co-selection measures, precision, recall, and F-score. In the evaluation phase, the system-generated summaries are categorized and tested based on their word sizes and the predetermined thresholds and compared against the human-generated summaries. The results indicate that the hybrid system performs better than the TF-IDF system even in lower thresholds, and also both systems are inclined to improve average F-scores in higher threshold generated summarization. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
  • Thumbnail Image
    Article
    Demographic Features of Turkish Literature Audiences and Applied Analysis of the Factors Affecting Their Reading Preferences
    (American-Eurasian Network for Scientific Information, 2014) Poyraz,Y.; Korkmaz,M.; Yücel,A.S.; Aras,G.; Çelebi,N.
    The purpose of this study is to determine factors affecting reading preferences in parallel with the demographic features of Turkish literature audiences. The study lasted approximately for 7 months. (N=650) individuals attended the study in total. The universe of the study is Turkey while the sample of the study is composed of 8 different provinces. These provinces are Istanbul, Ankara, Izmir, Bursa, Kocaeli, Sakarya, Trabzon and Gaziantep. A questionnaire form whose reliability and validity had been ensured before and which was composed of 5 point Likert scale was used in the study. The questionnaire form was reformed in accordance with the topic of the study, it was subjected to validity and reliability test and it was carried into main practice through taking views of experts. Data acquired from the results of main practice was analyzed by using SPSS 18.0 packet program and the value of 0.924 was acquired as Cronbach’s Alpha co-efficient. This value indicates that the measuring tool used in this study is quite reliable. The questionnaire is composed of two sections. In the first section, there are questions with regard to determine demographic features of the participants while in the second section, there are scaled questions composed of 120 items. 0.05 of significance level was taken into account among variables in terms of relations and differences. Methods such as different statistics anova, factor and hypothesis tests were applied in the analysis. Moreover, 4 different literary works were mentioned in the study so as to determine attitudes and behaviors of the participants towards literary works. Opinions of the participants were demanded about novels such as Intibah (Rebirth), Araba Sevdasi (Ambition for Car), Mai ve Siyah (Blue and Black) and Çalikusu (The Wren). At the end of the study, it was found out that the participants followed academic publications more frequently, the use of computer and internet had an effect on reading e-book and up-to-date books were read more than those books written in a foreign or ancient language (Ottoman Turkish). Furthermore, it was determined that education and age variables of the participants had an effect on reading habits while gender, age and education variables had an effect in some reading factors. © 2014 AENSI Publisher All rights reserved.