The Use of Psycholinguistic Patterns in Interactive Systems of Active Information Retrieval

Valery Evgenevich Sachkov,Dmitry Aleksandrovich Akimov,Sergey Aleksandrovich Pavelyev

doi:10.14419/ijet.v7i4.38.24595

Valery Evgenevich Sachkov, Dmitry Aleksandrovich Akimov + Show 1 more

Open Access

https://doi.org/10.14419/ijet.v7i4.38.24595

Copy DOI

Abstract

The article explores the possibility of using psycholinguistic patterns in a dialogue with the Internet visitors. The scheme of the semantic kernel is shown for the purpose-setting installation of the search system and the methodology for constructing patterns, taking into account the psycholinguistic features of constructing a dialogue for obtaining the required information. The model of building psycholinguistic patterns for revealing the semantic information in dialogues is given. Patterns are based on associative links of words and word combinations. Such associative connections allow expanding the list of related words and revealing key information in the best way from short messages. The use of such a method in interactive active search systems makes it possible to improve information exchange and achieve a higher level of identifying the purpose of the dialogue.

Highlights

When searching for information, search engines use text or other information that has already been published on the Internet in the form of content
Artificial Intelligence Markup Language (AIML) is an artificial intelligence markup language that is compatible with XML, which allows you to create virtual interlocutors [1]
This markup language accelerates the creation of a dialog system, to which the Associative-semantic text preprocessor (ASTP) preprocessor will be applied, for the associative-semantic search

Summary

Introduction

When searching for information, search engines use text or other information that has already been published on the Internet in the form of content. When creating "Eliza", "A.L.I.C.E", etc. systems, the key moment was always the possibility of understanding the "meaning" of the user's query in natural language, respectively, the need to create a tool that can identify from the text, which the user asks the system and reorganize this information to a formal and comprehensible view handling by the computer is still an actual problem

Methods

Results

Conclusion