Development of the method for filtering verbal noise while search keywords for the English text

Abstract

<p><em>The object of research is the processing of verbal information to identify keywords in the text. The most important step in the search for key terms is the calculation of their weights in the document in question, which makes it possible to evaluate their significance relative to each other in this context. To solve this problem, there are many approaches that are conditionally divided into two groups: they require learning and do not require learning. Learning implies the need to pre-process the original body of texts in order to extract information about the frequency of occurrence of terms in the entire body. An alternative approach is using linguistic ontologies, which are more or less approximate models of the existing set of words in a given language. On the basis of both approaches, systems are created for the automatic extraction of key terms. Nevertheless, in the direction of searching for keywords, research is not stopped in order to improve the accuracy and completeness of the results, as well as to use methods of extracting information from the text to solve new problems.</em></p><p><em>Existing approaches to the definition of keywords are characterized. The best quality of text processing is achieved by linguistic methods or when their combinations are statistical. A system for automatically determining key phrases from natural language text should be developed using the morphological dictionary and syntax rules.</em></p><em>The study uses an approach to defining keywords based on finding syntactic links between word forms in sentences in English text using the instrumental capabilities of modern linguistic packages. In the framework of the general approach to reducing verbal noise in the method, it is proposed that it is achieved with the help of formalized operations: the replacement of pronouns with the corresponding nouns; removal of noise connections; removing noise words; withdrawal of stop words. The described operations can be used as additional modules that improve the results of finding keywords for both the developed method for determining keywords of English text and other algorithms for finding keywords.</em>

Authors and Affiliations

Oleg Bisikalo, Alexander Yahimovich, Yaroslav Yahimovich

Keywords

Related Articles

Laboratory studies of the coagulation process of waste waters of milk processing enterprises by changing the mixing rate

<p><em>The object of research is the process of mixing the coagulant with the waste water of the milk processing industry by means of a stirrer at different speeds of rotation. In case of incomplete mixing, there is a lo...

Improvement of the emissional component of the banking system as the factor of activation of the investment process

<p><em>The object of research is the banking system aimed at supporting the investment processes of the national economy of Ukraine. It is promising to conduct a study on developing proposals for the speedy reform of the...

Analysis of modern approaches to the formation of the portfolio investor shares stock

<p><em>The object of research is an investment portfolio consisting of a set of investment instruments (securities, assets, projects, etc.) in which the investor's finances are distributed. The main purpose of forming an...

The analysis of methodical approaches of the risk assessment organization

<p class="20CxSpFirst"><em>The object of research is methods of approach to risk assessment, each organization independently develops and implements. The author provides practically gained experience in an international...

Methodological approaches in development of value estimation of costs of freshwater resources of the water basin by the objects of nature use

<p><em>In the present work, the object of research is the cost evaluation of freshwater resources in the implementation of various economic activities within the boundaries of Ukraine's water basins.</em></p><p><em>It is...

Download PDF file
  • EP ID EP527548
  • DOI 10.15587/2312-8372.2018.149962
  • Views 102
  • Downloads 0

How To Cite

Oleg Bisikalo, Alexander Yahimovich, Yaroslav Yahimovich (2018). Development of the method for filtering verbal noise while search keywords for the English text. Технологический аудит и резервы производства, 6(2), 33-41. https://europub.co.uk/articles/-A-527548