The Use of Artificial Neural Networks for Solving Classification Problems in the Processing of Scientific Texts (Using the Example of Weka)

With the advent of deep learning technologies and their application in natural language processing, the accuracy of these methods has been improved in two main directions: using a neural network with a teacher to train a classifier and without a teacher to optimize data preprocessing and selection of characteristics. Over the past few years, neural networks have re-emerged as powerful machine learning models, and have shown better results in areas such as pattern recognition and speech processing. More recently, neural network models have also been applied to various natural language processing tasks with very good results. The study involves the consideration of the method of training a neural network with a teacher to classify scientific articles by belonging to one or another scientific journal.