3 results
Search Results
Now showing 1 - 3 of 3
Article Citation - WoS: 29Citation - Scopus: 43Text Classification Using Improved Bidirectional Transformer(Wiley, 2022) Tezgider, Murat; Yıldız, Beytullah; Yildiz, Beytullah; Aydin, Galip; Yıldız, BeytullahText data have an important place in our daily life. A huge amount of text data is generated everyday. As a result, automation becomes necessary to handle these large text data. Recently, we are witnessing important developments with the adaptation of new approaches in text processing. Attention mechanisms and transformers are emerging as methods with significant potential for text processing. In this study, we introduced a bidirectional transformer (BiTransformer) constructed using two transformer encoder blocks that utilize bidirectional position encoding to take into account the forward and backward position information of text data. We also created models to evaluate the contribution of attention mechanisms to the classification process. Four models, including long short term memory, attention, transformer, and BiTransformer, were used to conduct experiments on a large Turkish text dataset consisting of 30 categories. The effect of using pretrained embedding on models was also investigated. Experimental results show that the classification models using transformer and attention give promising results compared with classical deep learning models. We observed that the BiTransformer we proposed showed superior performance in text classification.Conference Object Emotion Analysis on Turkish Texts: a Systematic Mapping Study(Institute of Electrical and Electronics Engineers Inc., 2022) Altmay,G.; Turhan,C.In recent years, the increase in internet usage also led to an increase in data. Therefore, the importance of classification has increased to understand and analyze the data more easily, and this made emotion analysis a necessity. Research in this area shows that emotion is a key tool in analyzing texts. However, there are very limited studies conducted on the text in Turkish language. The purpose of this study is to detect emotions in Turkish texts by analyzing the results of earlier studies in this scope. The following research questions are aimed to be answered: What are the years and count of publications What are the techniques used in the emotion analysis on texts What are the main data sets Which types of emotion are detected Which tools are used in emotion analysis For this reason, a systematic mapping study is performed to categorize and summarize the existing literature on emotion analysis. To ensure relevant papers in this field, an automated search process is performed for this study. Web of Science and Scopus databases are used for searching current and past research in emotion analysis on texts. There are 66 articles found on this subject. Then, by using filtering, irrelevant studies are removed. According to a set of inclusion and exclusion criteria, 9 relevant papers are selected in this field. The machine learning method is used for text analysis that automatically identifies the patterns and makes decisions about emotions. © 2022 IEEE.Article Citation - WoS: 9Citation - Scopus: 13Improving Word Embedding Quality With Innovative Automated Approaches To Hyperparameters(Wiley, 2021) Yildiz, Beytullah; Yıldız, Beytullah; Tezgider, Murat; Yıldız, BeytullahDeep learning practices have a great impact in many areas. Big data and significant hardware developments are the main reasons behind deep learning success. Recent advances in deep learning have led to significant improvements in text analysis and classification. Progress in the quality of word representation is an important factor among these improvements. In this study, we aimed to develop word2vec word representation, also called embedding, by automatically optimizing hyperparameters. Minimum word count, vector size, window size, negative sample, and iteration number were used to improve word embedding. We introduce two approaches for setting hyperparameters that are faster than grid search and random search. Word embeddings were created using documents of approximately 300 million words. We measured the quality of word embedding using a deep learning classification model on documents of 10 different classes. It was observed that the optimization of the values of hyperparameters alone increased classification success by 9%. In addition, we demonstrate the benefits of our approaches by comparing the semantic and syntactic relations between word embedding using default and optimized hyperparameters.
