UDC 004.912
EXPERIMENTAL STUDY OF SUITABILITY OF PAPER ABSTRACTS TO RUSSIAN-ENGLISH HYBRID MACHINE
TRANSLATION BEFORE AND AFTER AUTOMATIC PRE-EDITING
V. M. Glushan, Dr. Sc. (Tech.), full professor of Department of CAD, ICTIS, SFEDU, Taganrog, Russia;
orcid.org/0000-0001-5822-9295, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
V. S. Kornilov, postgraduate student ICTIS, SFEDU, Taganrog, Russia;
orcid.org/0000-0003-4151-5740, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
A. Yu. Lozovoy, Ph.D. (Ped.), Associate Professor, Department of Foreign Languages of IMES of SFedU, Taganrog, Russia;
orcid.org/0000-0002-6701-3098, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The Problem of experimental Definition of Suitability of Translation of Russian-language Abstracts of scientific Articles into English using Russian-English Hybrid Machine Translator before and after the Procedure of automatic Pre-editing of the Source Text is considered. Modern Tools of Machine Translation provide relatively Low Quality. Therefore, all of the Increasing Trends of communicative Scientific Interaction make the Task of improving the Quality of Machine Translation timely and relevant. The Solution of this Problem is offered by the Analysis and Correction at various Stages of Text Information Processing. The Aim of the Work is to study the Suitability of Russian-language Abstracts of Scientific Articles for translation into English with the help of Russian-English Hybrid Machine Translator before and after the Procedure of automatic Pre-editing of the Source Text. In the study of Suitability, the current Standardization Rules PR 50.1.027-2014 «Pravila okazaniya perevodcheskih i osobyh vidov lingvisticheskih uslug» (Rules for the Provision of Translation and special types of Linguistic Services – in Russian) are used. To define the Quality of the Translation, the Total Number of EP (Error Points) and TQI (Translation Quality Index) were used. The Differences between formatted and unformatted Source Text, as well as the Procedures for Validation of Suitability and automatic Preediting of the Text are shown. As a Result, it was found that the Increase in the Total Number of Suitable Abstracts for Machine Translation after the automatic Pre-editing Procedure is 18 %.
Key words: Machine Translation, Translation Quality, Text Pre-editing, Text Translation, Linguistic Services, Abstracts, Text Complexity, Natural Language Processing, Text Information Processing.