5 results
Search Results
Now showing 1 - 5 of 5
Item Open Access KAZAKH HANDWRITING RECOGNITION(СДУ хабаршысы - 2023, 2023) Bazarkulova A.; Mutalivev Y.; Chazhabayev A.; Telman D. ; Bazarkulova D.Abstract. Recognition of handwritten text is one aspect of object recognition and known as handwriting detection cause of a computer’s potential to recognize and comprehend readable handwriting from resources including paper files, touch smart devices, images, etc. Data is categorized into a number of classes or groups using pattern recognition. The paper presents a successful experiment in recognizing handwritten Kazakh text using Convolutional Recurrent Neural Network based architectures and the Kazakh Autonomous Handwritten Text Dataset. The proposed algorithm achieved an overall accuracy of 86.36% and showed promising results. However, the paper suggests that further research could be conducted to improve the model, such as correlating and enlarging the database or incorporating other models and libraries. Additionally, the paper emphasizes the importance of considering language specifics when building a text recognition model, as modern algorithms that work well in one language may not guarantee the same performance in another.Item Open Access Speech Recognition of Kazakh Language(Faculty of Engineering and Natural Science, 2020) Aitimov K.In this research, an overage implementation of speech recognition revised. Here you can find algorithms and logic of how to convert digital signal into reasonable text. In common, all the signals recorded in m4a file format. You also will learn how to convert sound waves into digital signals, so you can use it wherever you like. In our days IT, technologies are expanding in an exponential level. There are many robots, which can understand human speech. Why we can’t create one of our own? Kazakh language will also be presented in technology world. That is our goal!Item Open Access KAZAKH LANGUAGE-BASED QUESTION ANSWERING SYSTEM USING DEEP LEARNING APPROACH(СДУ хабаршысы - 2023, 2023) Bilakhanova A. ; Ydyrvs A.; Sultanova N.Abstract. Deep learning advances have resulted in considerable gains in a variety of natural language processing applications, including questionanswering (QA) systems. QA systems are intended to retrieve data from big datasets and respond to user queries using natural language. Deep learning-based techniques have yielded encouraging results in the development of QA systems capable of providing consistent answers to a wide range of inquiries. This research presents a deep learning-based Kazakh language-based QA system. A pre-processing module is also included in the proposed system to improve the quality of the input text and the accuracy of the final output. The results reveal that the system has a high level of accuracy. This study promotes to the advancement of question-answering technology and contributes to the development of natural language processing tools in the Kazakh language.Item Open Access COMPARISON OF DIFFERENT CLASSIFICATION MODELS FOR SENTIMENT ANALYSIS(СДУ хабаршысы - 2023, 2023) Makhul M.Abstract. In this work, we explored sentiment analysis techniques of texts using the example of product comments in the Kazakh language. To do this, we used machine learning methods such as Naive Bayes, Random Forest, Logistic Regression and Support Vector Machine, as well as text processing tools: CountVectorizer and TfidfVectorizer. In the process of work, experiments were carried out with different configurations of models and parameters of vectorizers. To assess the quality of the models, we used accuracy, precision, recall and F1-score metrics. The research findings indicated that the application of machine learning techniques make it possible to achieve high accuracy in sentiment analysis of comments. The best results were obtained using the Support Vector Machine and TfidfVectorizer. This study can be used to further improve the systems for sentiment analysis of comments in the Kazakh language, which can be useful in monitoring public opinion in various areas, including business.Item Open Access FAST AND RELATIVELY ACCURATE SENTIMENT ANALYSIS FOR THE KAZAKH LANGUAGE(2022 International Young Scholars' Conference, 2022) N. ManteyevaAbstract This paper constructs a fast and accurate sentiment analysis model for the Kazakh language. The main method for text classification is based on TF-IDF-based tokens trained with Logistic Regression. The processing and modeling stages are fully implemented in the PySpark framework. The proposed method has shown an accuracy level of 82% on an evenly distributed test dataset. As a byproduct of the work, we have collected a list of words in the Kazakh language that could signal the negativity/positivity of the given review.