Introduction

Abstract

The information world that we live in today presents us with a vast amount of data stored separately in books, newspapers, audio and video records of numerous different formats, internet and other media, all of them increasingly digitized. Moreover, there is an exponential increase in the number of these data, causing the capability of an average computer-literate person to find specific data or useful topic-related information to decrease rapidly. The negative impact these vast amounts of data have on finding relevant information could be partially alleviated by using efficient techniques for information structuring and retrieval. Popular search engines nowadays, however, still very often fail to retrieve documents relevant to the query. The algorithms of these search engines, namely, still mostly rely on keyword matching, regardless of the variety of individual meanings of the keywords, the complex meanings arising from the combinations of keywords into phrases, or even different meanings that occur when keywords and phrases are used in different contexts.