Full Program »
Data Extraction and Preprocessing for Automated Question Answering Based on Knowledge Graphs
This article discusses the algorithms and methods of data representation for knowledge graphs. The proposed algorithms make it possible to automate the process of extracting and processing data from users' requests within the mixed learning process and reduce the role of an expert in the preparation of question-answering data sets necessary for training models of dialogue systems. The results show that the method of enrichment of the knowledge graph leads to an increase in the number of links and the accuracy of vector representation models.