A Post-Editing Practice Report Of Machine Translation For Science News In The Economist

Due to the rapid development of software technology,the emergence of new algorithms and the improvement of computer performance,machine translation technology has made tremendous progress today.Machine translation has been widely recognized by the translation industry and customers,and it has become an important aid for efficient translation.The use of machine translation is becoming more and more widespread in translation activities at present,and its role and influence cannot be underestimated.Some experts even predict that it will replace human translation in the future.In the author’s translation practice,he found that the machine translation tool “Google Online Translate” could indeed help translators solve certain problems.Although the translation of different texts may cause major or minor errors,it still required manual post-editing work to guarantee the quality of translation.Here,the author took the English-Chinese translation of scientific and technological text as an example to test the translation performance of Google’s online translation in specific text types.The author counted the typical translation errors of Google translation in such texts and summarized the errors in machine translation in scientific and technological text.In this translation practice,the author summarized the errors of machine translation from the four levels of vocabulary,phrase,clause and format,such as word selection errors,phrase mistranslation,clause mistranslation,and translation inconsistencies.After analysing the reasons that cause these errors,the author proposed logical analysis,correct division of sentence meaning groups,correct division of sentence structure,and use of CAT tools to check punctuation and other post-editing strategies to improve the quality of machine output.