The aim of the research was to debunk those common myths and prejudices associated with MT that have been widespread since the 1950s and determine where it can sit within a localization project.
The apprehension as to whether MT can work for marketing content is often based on unproven prejudices that have built over the years in and outside of the localization industry.
Within this study, we compared and evaluated five of the leading Machine Translation providers – Amazon Translate, DeepL, Google Cloud, Microsoft Translator, and ModernMT.
The MT tools were tested on their accuracy and reliability in translating 168 different segments containing more than 1,000 different words from American English into French, German, Spanish, Simplified Chinese, Arabic, and European Portuguese.
Reviewed by professional linguists, 85% of the 14 translations were scored as ‘Very good’ or ‘Acceptable’, with none of the machine-translated material scored as ‘Very bad’.
Italian was the most difficult language to translate, while German scored the highest.
Of the 168 different word segments tested on the software, German again came out on top, with 145 sections not requiring any edits from the professional linguists after being translated, compared to Portuguese which had just 58 unedited sections.
10 out of the 14 total reviews of the quality of the translations were scored as being “positively surprised” by the professional linguists who participated in the study, with the MT output of better quality than originally expected.
At Weglot, using machine translation as part of a website translation project is built into our product. We’ve seen thousands of users benefit from its speed and accuracy and use it combined with post-editing, with on average 30% of content being edited.
The findings presented in the study open a perspective of machine translation as a highly effective way to translate a website. We concluded that machine translation has reached a certain level of maturity where it now complements human linguists.
Read the machine translation report for the detailed results.