A Critical Evaluation of Translation Quality and Post-Editing Performance of Fastdic Translator

This study aimed to critically assess the translation quality of Fastdic Translator, a domestic machine translation, using Wilss’s (1982) matrix, which evaluates syntax, semantics, and pragmatics, to identify the system’s strengths and weaknesses. Additionally, ChatGPT was utilized to determine if the translations generated by Fastdic Translator required post-editing and to assess whether ChatGPT could serve as a reliable AI tool for translators and end-users, potentially replacing human editors. The research involved a translation test of 80 sentences, chosen from Mistrík’s (1997) text type classifications, including narrative, descriptive, and argumentative styles, with idiomatic expressions added by the researcher. Fastdic Translator first translated these sentences from English into Persian. Both the original English text and the Persian translations were provided to evaluators, who evaluated the translation quality using a Likert-scale questionnaire. The results indicated that while Fastdic Translator produced grammatically sound Persian translations, there were occasional issues with subject-verb agreement, especially in more complex sentences. Semantically, the translations were generally accurate. However, in the pragmatic evaluation, the system struggled, particularly with idiomatic expressions and implied meanings, producing inappropriate translations. The findings also revealed that post-editing with ChatGPT significantly improved the translations by correcting errors and better conveying the intended meaning while ensuring grammatical accuracy. Therefore, ChatGPT can be seen as a powerful and reliable AI editor for both end-users and translators. Keywords: Machine Translation, Fastdic Translator, Wilss’s Matrix, Translation Evaluation