St.Petersburg, Russia
November 14–15, 2019

Talks & master-classes

Development of the Automatic Text Analysis Framework for the Russian Language and its Application for Software Tools

  • Programming / Tools
  • Voice Interfaces / Natural lang. processing
  • Accepted

November 14, 13:30
Room III
Add to gCal    Add to iCal/Outlook

Discuss the presentation

The use of linguistic analysis based on the accumulated experience in the field of computer linguistics allows us to simplify processing of huge amounts of text information and opens up new opportunities for automating text documents processing.

There is a problem of finding suitable tools, adapting them to work with texts in the Russian language, and integrating with each other makes it difficult to use them both for research purposes and in industrial systems, therefore, we present a new open source Java framework TAWT that provides convenient ready-made tools and data structures for the main stages of text analysis for the Russian language which meets modern requirements for performance, reliability, project assembly tools, etc., the framework is demonstrated on automating some technical documentation tasks.

The framework is demonstrated on the example of automating some technical documentation preparation tasks, TAWT can be useful for developers of research tools or applied software for implementing new functions or improving the quality of text processing by applying linguistic analysis methods, as well as for developers of automated tools to reduce routine tasks working with different types of documentation.

Ekaterina Politsyna photo|Екатерина Полицына фото

Ekaterina Politsyna

Associate Professor, Moscow Aviation Institute

Graduated from the MATI-RSTU named after K.E. Tsiolkovsky, the department “Computer systems design”, PhD in technical sciences. More than 10 years of experience in software development, system design, project management in a number of companies. More than 14 years in the field of scientific research in computer linguistics developing algorithms and tools for automatic text processing in Russian. Participant of Russian and international conferences and competitions.


Sergey Politsyn

Associate Professor, Moscow Aviation Institute

Graduated from the MATI-RSTU named after K.E. Tsiolkovsky, the department “Computer systems design”, PhD in technical sciences. More than 10 years of experience in software development, test automation, and project management. Co-researcher in computer linguistics. Participant of Russian and international conferences and competitions.


Alexander Porechny

Postgraduate student, Moscow Aviation Institute

Postgraduate student of the Moscow Aviation Institute (National Research University), department of “Intellectual Monitoring Systems”. At the present time a server software developer. Has practical experience in developing applications based on the microservice architecture and load testing. Engaged in research and development of computer linguistics software for more than 3 years. Participant of Russian and international conferences.