2 results
Search Results
Now showing 1 - 2 of 2
Item Open Access Classification of Scientific Documents in the Kazakh Language Using Deep Neural Networks and a Fusion of Images and Text(MDPI, 2022) Bogdanchikov A.; Ayazbayev D.; Varlamis I.The rapid development of natural language processing and deep learning techniques has boosted the performance of related algorithms in several linguistic and text mining tasks. Consequently, applications such as opinion mining, fake news detection or document classification that assign documents to predefined categories have significantly benefited from pre-trained language models, word or sentence embeddings, linguistic corpora, knowledge graphs and other resources that are in abundance for the more popular languages (e.g., English, Chinese, etc.). Less represented languages, such as the Kazakh language, balkan languages, etc., still lack the necessary linguistic resources and thus the performance of the respective methods is still low. In this work, we develop a model that classifies scientific papers written in the Kazakh language using both text and image information and demonstrate that this fusion of information can be beneficial for cases of languages that have limited resources for machine learning models’ training. With this fusion, we improve the classification accuracy by 4.4499% compared to the models that use only text or only image information. The successful use of the proposed method in scientific documents’ classification paves the way for more complex classification models and more application in other domains such as news classification, sentiment analysis, etc., in the Kazakh language.Item Open Access DEVELOPMENT OF IMAGE CAPTIONING MODEL BY USING DEEP LEARNING TOOLS(СДУ хабаршысы - 2019, 2019) Kynabay B. ; Aldabergen A. ; Shamiluulu S.Abstract. Automatic formation of image description is one of the most challenging and popular topics in the field of deep learning (DL) for nowadays. In this work image captioning convolutional neural network model (VGG16) is developed by implementing deep learning tools and techniques. Specifically, this work’s resulting product can be implemented in a system that answers to the question, based on the image given. Image captioning includes two main sub-processes: image processing and natural language processing. The model was constructed from 16 layers and it uses Flicker 8K data-set of images for captioning. The model was evaluated by using BLEU metric and its value was nearly 0.75, it takes one image as an input and returns one description for that image.