Browsing by Author "Hark, C."

Now showing 1 - 3 of 3

Çizge Benzerliǧi Yöntemi ile Doküman Siniflandirma
(Institute of Electrical and Electronics Engineers Inc., 2019) Uçkan, T.; Hark, C.; Seyyarer, E.; Ayata, F.; Karci, A.
The classification of the documents is at the beginning of the topics that are studied extensively today. Using text similarity, many areas are used, such as whether citations are quoted elsewhere or the information searched in search engines is fast and accurate. A variety of methods are used while looking for similarities between documents. Similarity measurements are made by two basic methods, word-based and sentence-based, during the comparison of several documents. While word-based similarity measurements are made, many distance measurement methods such as Jaccard, Dice, Cosine similarity are used. In this study, the paragraphs in different documents will be broken down by sentence basis and they will be represented by a graph, and a study will be done on the classification of the documents using Hamming distance measurements by XOR method of neighborhood matrices obtained from these documents. © 2018 IEEE.
Doǧal Dil İşleme Yaklaşimlari ile Yapisal Olmayan Dökümanlarin Benzerliǧi
(Institute of Electrical and Electronics Engineers Inc., 2017) Hark, C.; Seyyarer, A.; Uçkan, T.; Karci, A.
Unstructured document and archive stacks that are formed in the past years are growing in size faster these days and they need to be clarified with various methods. This increases the interest in natural language processing discipline day by day and makes it more popular. In this study, we've tried to calculate the similarities between document stacks, that no information is presented onbehalf of their similarities and are completely independent of each other. Text mining approaches have been utilized in order to calculate the similarities of non-structural documents given. For this purpose, 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. © 2017 IEEE.
Graph-Based Suggestion for Text Summarization
(Institute of Electrical and Electronics Engineers Inc., 2019) Hark, C.; Uçkan, T.; Seyyarer, E.; Karci, A.
One of the methods of text summarization within the context of Natural Language Processing (NLP) works is to summarize the text by selecting sentences from the original text. There are different approaches to summarize sentence selection. In this study, texts that do not have a certain structure have been preprocessed and transfer of the proposed diagram in a structured format in the form of an expression. Different feature extraction methods could be applied on the charts. Our method uses conceptually the diagrams obtained in the representation of the text. This study aims to suggest a method of summarization of texts with a linear weighting of the importance of sentences. Moreover, the method presented does not require the use of deep linguistic knowledge and this work can be adapted to different languages. © 2018 IEEE.