INVESTIGATION OF MACHINE TRANSLATION APPLICABILITY
The study evaluates the text complexity metrics applicability in assessing text fitness for machine translation (MT). Possible approaches to such assessments are discussed. The experiment used a corpus of research papers translated from Russian into English by both a professional translator and the...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Marina Sokolova Publishings
2020-06-01
|
Series: | Russian Linguistic Bulletin |
Subjects: | |
Online Access: | http://rulb.org/wp-content/uploads/wpem/pdf_compilations/2(22)/6-8.pdf |
id |
doaj-2d5e67b13146472c866a725ec7161300 |
---|---|
record_format |
Article |
spelling |
doaj-2d5e67b13146472c866a725ec71613002021-04-02T11:06:21ZengMarina Sokolova PublishingsRussian Linguistic Bulletin2313-02882411-29682020-06-0120202 (22)6810.18454/RULB.2020.22.2.3310.18454/RULB.2020.22.2.33INVESTIGATION OF MACHINE TRANSLATION APPLICABILITYStrakhova, D.A.0Tula State UniversityThe study evaluates the text complexity metrics applicability in assessing text fitness for machine translation (MT). Possible approaches to such assessments are discussed. The experiment used a corpus of research papers translated from Russian into English by both a professional translator and the DeepL MT engine. It is shown that the existing metrics cannot be used to forecast the MT quality since the MT output may be unusable even for low-complexity source texts. It is also proved that MT is unsuitable for almost 50% of the specialized text to be translated.http://rulb.org/wp-content/uploads/wpem/pdf_compilations/2(22)/6-8.pdfmachine translation qualitytext complexity metricsediting distancecat toolsmachine translation applicabilityкачество машинного переводапоказатели сложности текстарасстояние редактированияcat-инструментыприменимость машинного перевода |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Strakhova, D.A. |
spellingShingle |
Strakhova, D.A. INVESTIGATION OF MACHINE TRANSLATION APPLICABILITY Russian Linguistic Bulletin machine translation quality text complexity metrics editing distance cat tools machine translation applicability качество машинного перевода показатели сложности текста расстояние редактирования cat-инструменты применимость машинного перевода |
author_facet |
Strakhova, D.A. |
author_sort |
Strakhova, D.A. |
title |
INVESTIGATION OF MACHINE TRANSLATION APPLICABILITY |
title_short |
INVESTIGATION OF MACHINE TRANSLATION APPLICABILITY |
title_full |
INVESTIGATION OF MACHINE TRANSLATION APPLICABILITY |
title_fullStr |
INVESTIGATION OF MACHINE TRANSLATION APPLICABILITY |
title_full_unstemmed |
INVESTIGATION OF MACHINE TRANSLATION APPLICABILITY |
title_sort |
investigation of machine translation applicability |
publisher |
Marina Sokolova Publishings |
series |
Russian Linguistic Bulletin |
issn |
2313-0288 2411-2968 |
publishDate |
2020-06-01 |
description |
The study evaluates the text complexity metrics applicability in assessing text fitness for machine translation (MT). Possible approaches to such assessments are discussed. The experiment used a corpus of research papers translated from Russian into English by both a professional translator and the DeepL MT engine. It is shown that the existing metrics cannot be used to forecast the MT quality since the MT output may be unusable even for low-complexity source texts. It is also proved that MT is unsuitable for almost 50% of the specialized text to be translated. |
topic |
machine translation quality text complexity metrics editing distance cat tools machine translation applicability качество машинного перевода показатели сложности текста расстояние редактирования cat-инструменты применимость машинного перевода |
url |
http://rulb.org/wp-content/uploads/wpem/pdf_compilations/2(22)/6-8.pdf |
work_keys_str_mv |
AT strakhovada investigationofmachinetranslationapplicability |
_version_ |
1724165646636285952 |