Validation of the Reliability of Machine Translation for a Medical Article From Japanese to English Using DeepL Translator

Abstract

BackgroundThe reliability of DeepL Translator (DeepL GmbH, Cologne, Germany) for the translation for medical articles has not been verified yet. In this study, we investigated the accuracy of machine translation from Japanese to English for a medical article using the DeepL Translator. MethodologyThe subject of this study was an English-language medical article translated from Japanese, which had already been published. The original Japanese manuscript was translated into English using DeepL Translator. The translated English article was then back-translated into Japanese by three researchers. In turn, three other researchers compared the back-translated Japanese sentences with the original Japanese manuscript and calculated the percentage of sentences that retained the intended meaning. ResultsThe mean ± standard deviation of the match rate for the entire article was 94.0 ± 2.9%. The match rate in the Results section was significantly higher than that in the other sections; while the match rate in the Materials and Methods section was significantly lower than the rate in the other sections. Compound sentences and sentences with an unclear subject and predicate appeared to be significant predictors for mismatched translation. ConclusionsThe translation for a medical article from Japanese to English was performed accurately by DeepL Translator.

Is Machine Translation Reliable in the Legal Field? A Corpus-Based Critical Comparative Analysis for Teaching ESP at Tertiary Level

“…Also, word order needs improvement in the machine-translated text (see Table 4, line 3, for example). Contrary to what was remarked by Takakusagi et al (2021), there seems to be a correlation between the length of the text and the accuracy of MT. In particular, the longer the sentence, the higher the number of MT inaccuracies.…”

“…For these reasons, and given the growing importance of MT both in the translation and educational field (Almahasees, 2022;Lee, 2021;Rivera-Trigueros, 2021), the literature has recently focused on assessing the quality and reliability of several MT tools (Almahasees, 2022;Rivera-Trigueros, 2021;Takakusagi et al, 2021). Rivera-Trigueros (2021), for example, questions the performances of MT platforms such as Deepl and Google in English and Spanish.…”

ChatGPT and other artificial intelligence applications speed up scientific writing

“…In translation, AI has dramatically improved the accuracy of machine translation in recent years, with DeepL Translator (DeepL GmbH) being probably the leader. 15 DeepL Translator uses an algorithm called a convolutional neural network in deep learning. In August 2017, DeepL Translator launched the free online translation service.…”

Clinical practice guideline recommendations to improve the mental health of adult trauma patients: protocol for a systematic review

“…No language restriction will be applied. We will use an open-access online translator (https://www.deepl.com/translator) for studies not written in English of French 35. CGPs are defined as ‘statements that include recommendations intended to optimise patient care that are informed by a review of evidence and an assessment of benefits and harms of alternative care options’ 36.…”