Organization of Information System for Semantic Search Based on Associative Vector Space

Abstract

Text arrays, created by the online community, contain specific cognitive capabilities. Analyses cover the following: mass media materials, social networks, forums, blogs, political materials, biographies and diaries, scientific publications, belles-letters and other. As practice shows, standard search systems are not always able to find the required data out of this huge volume of the data file. A difficult task for the automated computer text processing is the semantic analysis, which is interpretation of meaning of the text, its content and semantics. Performance of this task requires knowledge of meaning of words and sentences; the way to describe these values formally, and to carry out operations with them, even their storage in computer memory, cause difficulties. That is why in automated text processing computer is not able to search texts of a certain subject, without explicitly specified keywords or phrases, as well as to find texts with the similar meaning, which is quite difficult for the search procedure. Modern information retrieval systems (IRS) are mainly based on key words. The major features for this approach are frequency of word occurrence in document collection, its uniqueness, morphological and syntactic properties. The problem is that the full-text information retrieval systems initially do not imply any semantic connection between the documents and the information they contain, and do not take into account the context and many other issues of importance for semantic interpretation, which makes full-text information retrieval systems unsuitable solution for contextual search. Semantic information retrieval systems should settle the issue of full-text IRS and assist the computer in formal description of semantic meaning of the documents and the data about it. This paper examines possible organization of semantic information-retrieval system based on associations, and uses associative vector spaces as the basic semantic structures.