February 2017, № 2 (202), pages 92–96

doi: 10.25198/1814-6457-2017-202-2-92-96

Perekhodko I.V., Myachin D.A. QUALITY EVALUATION OF COMPUTER TRANSLATIONThe following article considers the issue of language quality assessment of machine translation owing to the growing internet-communication on one side and the inadequate research of automatic translation, that aren't currently inadaptable, on the other side. Such a study reveals key reason of machine translation's mistakes. This article attempts to examine strategy of interaction “human-to-machine” in the translation and to analyse translated texts of web-sites executed by automatic systems, based on linguostylistic analysis and automated language processing with the use of METEOR on the lines of N-gram. Case study shows that the largest number of mistakes is due to translation of semantic constructions. The practical implications lies in the fact that the development of a system of quality assessment of machine translation makes it possible to identify and to systematize any shortcomings of software with a view to further development, since the automation of translation has become crucial, allowing for the accommodation of a higher workloadKey words: internet communication, machine translation, linguostylistic interpretation, lexical errors, syntax error, error of style.

Download

References:

1. Nikiforova, N.YU. Lingvopragmaticheskaya specifika reklamnyh tekstov v komp'yuterno-oposredovannom diskurse i priemy ih lokalizacii [EHlektronnyj resurs] / N.YU. Nikiforova // Vestnik VolGU. — Seriya 9: Issledovaniya molodyh uchenyh. — 2013. — №11. — URL: http://cyberleninka.ru/article/n/lingvopragmaticheskaya-spetsifika-reklamnyh-tekstov-v-kompyuterno-oposredovannom-diskurse-i-priemy-ih-lokalizatsii (data obrashcheniya: 27.12.2016).

2. Oxford University Press [EHlektronnyj resurs]. — Oxford Dictionariesa, 2016. — Rezhim dostupa: https://en.oxforddictionaries.com/

3. Babina, O.I. YAzykovaya lichnost' perevodchika i mashinnyj perevod [EHlektronnyj resurs] / O.I. Babina // Vestnik CHelGU. — 2011. — №24. — URL: http://cyberleninka.ru/article/n/yazykovaya-lichnost-perevodchika-i-mashinnyy-perevod (data obrashcheniya: 27.12.2016).

4. Densmer, L. Light and Full MT Post-Editing Explained / MORAVIA [EHlektronnyj resurs] / L. Densmer. — Rezhim dostupa: http://info.moravia.com/blog/bid/353532/Light-and-Full-MT-Post-Editing-.

5. CHakyrova, YU.I. Postredaktirovanie v translatologicheskoj paradigme [EHlektronnyj resurs] / YU.I. CHakyrova // Vestnik PNIPU. Problemy yazykoznaniya i pedagogiki. — 2013. — №8. — URL: http://cyberleninka.ru/article/n/postredaktirovanie-v-translatologicheskoy-paradigme (data obrashcheniya: 27.12.2016).

6. Nagao, M. A New Method of N-gram Statistics for Large Number of n and Automatic Extraction of Words and Phrases from Large Text Data of Japanese / M. Nagao, S. Mori // In Proceedings of the 15th International Conference on Computational Linguistics (COLING 1994). — Kyoto, Japan, 1994.

About this article

Authors: Perehodko I.V., Myachin D.A.

Year: 2017

doi: 10.25198/1814-6457-2017-202-2-92-96

Editor-in-chief

Sergey Aleksandrovich
MIROSHNIKOV

© Электронное периодическое издание: ВЕСТНИК ОГУ on-line (VESTNIK OSU on-line), ISSN on-line 1814-6465
Зарегистрировано в Федеральной службе по надзору в сфере связи, информационных технологий и массовых коммуникаций
Свидетельство о регистрации СМИ: Эл № ФС77-37678 от 29 сентября 2009 г.
Учредитель: Оренбургский государственный университет (ОГУ)
Главный редактор: С.А. Мирошников
Адрес редакции: 460018, г. Оренбург, проспект Победы, д. 13, к. 2335
Тел./факс: (3532)37-27-78 E-mail: vestnik@mail.osu.ru