Knowledge Base Collecting Using Natural Language Processing Algorithms

Natural language processing (NLP) is one of the most complicated and fast developing area in Computer Science. There are solutions in this area for special cases, but developing one general solution is impossible due to variety of grammatical, syntactic and semantic forms in different languages. The NLP algorithms and methods are used in speech recognition, text analyzing and understanding, speech generation. This paper is focused on application of NLP approaches to understand quasi-structured or unstructured data with subsequent inclusion in a knowledge base. The article covers the usage of a graph database as a knowledge base, that allows to show and visualize relationships between different pieces of text according to specified data patterns.