Skip to Main Content

Modelling and Data Analysis
2023. Vol. 13, no. 1, 19–24
https://doi.org/10.17759/mda.2023130102
ISSN: 2219-3758 / 2311-9454 (online)

Text Detoxification System in Dialogue Conversations

 
Audio is AI-generated
168

,

PDF (RUS)
Online translation in english
GS
Information
in Google Scholar
Metrics

Abstract

The work is aimed at improving the cultural level of correspondence in dialog systems. The key feature of the work is its focus on real–time use and ensuring sustainable detoxification, taking into account the specifics of dialog communication (typos, noise symbols, transliteration, etc.). The solution offers the use of a neural network approach and software processing to obtain embeds of tokens and the subsequent solution of the classification problem. Unlike traditional message filters, the task is to preserve the meaning of the source text by clearing it of toxic content. The operability of the system can be checked on the basis of the Telegram messenger, in which the model is presented in the form of a bot. The system itself is deployed on the basis of Serverless technology from a cloud provider, which allows it to adapt to peak loads and at the same time be easy to maintain.

General Information

Keywords: detoxification of text, neural networks, serverless

Journal rubric: Data Analysis

OpenAlex citations: 0

OpenAlex trends: Discourse Analysis and Cultural Communication, Advanced Research in Systems and Signal Processing, Scientific Research and Philosophical Inquiry

Information about the work in OpenAlex

Number of citations: 0

Topics

Discourse Analysis and Cultural Communication

This cluster of papers focuses on discourse analysis, cultural communication patterns, and language use in the context of the pandemic. It explores topics such as media representation, persuasion strategies, linguistic aspects of pandemics, and the impact of social media on language and culture.

Number of works: 106512  |  Total number of citations: 87483

Topic detailsв OpenAlex

Advanced Research in Systems and Signal Processing

This cluster of papers focuses on the integration of cyber, physical, and social systems, with an emphasis on decision making, urban computing, autodyne sensors, machine learning, data mining, transportation systems, information management, parallel computing, and infrastructure development.

Number of works: 31317  |  Total number of citations: 164598

Topic detailsв OpenAlex

Scientific Research and Philosophical Inquiry

This cluster of papers covers a wide range of topics related to information science and technology development, including the impact of digital technology, foresight methods, knowledge management, big data, innovation, media, ontology, and semantic search. The papers explore the intersection of information science with various fields such as economics, education, neuroscience, sociology, and environmental studies.

Number of works: 44007  |  Total number of citations: 112893

Topic detailsв OpenAlex

Work details in OpenAlex

Article type: scientific article

DOI: https://doi.org/10.17759/mda.2023130102

Received 17.01.2023

Accepted

Published

For citation: Suvorov, M.D., Vinogradov, V.I. (2023). Text Detoxification System in Dialogue Conversations. Modelling and Data Analysis, 13(1), 19–24. (In Russ.). https://doi.org/10.17759/mda.2023130102

© Suvorov M.D., Vinogradov V.I., 2023

License: CC BY-NC 4.0

References

  1. Rubtsova Yu.V. Automatic construction and analysis of the corpus of short texts (microblogging posts) for the task of developing and training a tone classifier //Knowledge engineering and semantic web technologies. - 2012. – Vol. 1. – pp. 109-116.

Information About the Authors

Mariam D. Suvorov, student, Moscow Aviation Institute (National Research University) (MAI), Moscow, Russian Federation, ORCID: https://orcid.org/0000-0002-8376-0448, e-mail: msuvorov7@gmail.com

Vladimir I. Vinogradov, Candidate of Science (Physics and Matematics), Associate Professor, Department of Mathematical Cybernetics, Moscow Aviation Institute (National Research University), Moscow, Russian Federation, ORCID: https://orcid.org/0000-0003-3773-9653, e-mail: vvinogradov@inbox.ru

Metrics

 Web Views

Whole time: 378
Previous month: 12
Current month: 9

 PDF Downloads

Whole time: 168
Previous month: 6
Current month: 8

 Total

Whole time: 546
Previous month: 18
Current month: 17