A Critical Evaluation of Translation Quality and Post-Editing Performance of Fastdic Translator
Main Article Content
Abstract
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
Downloads
Article Details

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).