Concept Based Representations as Complement of Bag of Words in Information Retrieval

Abstract

Abstract. Information Retrieval models, which do not represent texts merely as collections of the words they contain, but rather as collections of the concepts they contain through synonym sets or latent dimensions, are known as Bag-of-Concepts (BoC) representations. In this paper we use random indexing, which uses co-occurrence information among words to generate semantic context vectors and then represent the documents and queries as BoC. In addition, we use a novel representation, Holographic Reduced Representation, previously proposed in cognitive models, which can encode relations between words. We show that these representations can be successfully used in information retrieval, can associate terms, and when they are combined with the traditional vector space model, they improve effectiveness, in terms of mean average precision.

Development of a method for determining the indicators of manipulation based on morphological synthesis

“…The main difference between the known approaches to processing natural-language texts in order to automate the process of their analysis lies in the ways of presenting and analyzing the content of such texts. One approach is based on the assumption that the main content of the text is determined by a set of keywords (Bag of Words) [18]. This approach does not take into account the linguistic relationships and semantics of the natural language, but allows you to quickly process the text according to formal features.…”

Photo Content of Communication Platforms as a Mechanism of Opposing Russian Propaganda (On the Example of the Ukrainian War of Liberation)

“…Among other things should be mention that the propaganda material should stand out among other irritants that are currently operating, as follows − possess a sufficient duration of action; sufficient intensity and novelty. The material itself has a great influence on memorization: the more meaningful, logical, emotionally colored it is, the better it is fixed in memory (Carrillo, 2010).…”

Real-Time Context Based Information Retrieval Using Semantic and Features on Streaming Content

“…Concept based retrieval systems are currently in the raise, that are similar to the content based retrieval system. The current contributions in this area includes educational resource identification [14], a portal retrieval engine [15] and a generic system using bag of words retrieval technique [16].…”