Claim Missing Document
Check
Articles

Found 2 Documents
Search

Abstractive summarization using multilingual text-to-text transfer transformer for the Turkish text Alipour, Neda; Aydın, Serdar
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 2: April 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i2.pp1587-1596

Abstract

Today, with the increase in text data, the application of automatic techniques such as automatic text summarization, which is one of the most critical natural language processing (NLP) tasks, has attracted even more attention and led to more research in this area. Nowadays, with the developments in deep learning, pre-trained sequence-to-sequence (text-to-text transfer converter (T5) and bidirectional encoder representations from transformers (BERT) algorithm) encoder-decoder models are used to obtain the most advanced results. However, most of the studies were done in the English language. With the help of the recently emerging monolingual BERT model and multilingual pre-trained sequence-to-sequence models, it has led to the use of state-of-the-art models in languages with fewer resources and studies, such as Turkish. This article used two datasets for Turkish text summarization. First, Google multilingual text-to-text transfer transformer (mT5)-small model was applied on multilingual summarization (MLSUM), which is a large-scale Turkish news dataset, and success was examined. Then, success was evaluated by first applying BERT extractive summarization and then abstractive summarization on 1010 articles collected on the Dergipark site. Rouge measures were used for performance evaluation. This study is one of the first examples in the Turkish language and it is considered to provide a basis for future studies with good results.
Exploring AutoText Summarization Methods in Turkish: A Literature Review Alipour, Neda; Pourmousa, Hadi; Naserinia, Mohammad
The Indonesian Journal of Computer Science Vol. 14 No. 2 (2025): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v14i2.4803

Abstract

In recent years, the huge volume of textual data has become a challenge, as this challenge is seen in various fields, including scientific articles, legal documents, Internet archives, and even online product reviews. Given the limited data processing capacity of humans, processing large amounts of data is impractical and causes confusion; on the other hand, it requires a lot of effort, which ultimately results in a waste of time. To overcome this problem, the need to implement automated techniques such as automatic text summarization has emerged. Automated text summarization is an automated technique used to create a more condensed version of the original content that provides the same meaning and information. In fact, the generated output should contain important information from the original document. Various techniques for automatic summarization have been proposed in studies. Many studies have been presented on automatic text summarization methods, however, limited papers have contributed to reviewing different techniques of summarization methods in different languages, so this topic is evolving to reach maturity. This study focuses on different automatic text summarization methods in Turkish by reviewing the literature and previous studies, thus analyzing the performance of automatic text summarization methods.