The level of achievement of Iranian developers in local machine translation systems: Focusing on quality and post-editing

Abstract

Localized machine translation technologies have been developed to address region specific linguistic needs, yet they remain less widely adopted than dominant global systems. Despite their potential, limited evidence exists regarding their translation quality, particularly in complex communicative contexts. This study addresses this gap by evaluating the performance of three domestic machine translation systems and examining their strengths, limitations, and overall reliability in English to Persian translation. A set of eighty test statements representing narrative, descriptive, argumentative, and idiomatic forms was used to assess linguistic accuracy across grammatical, semantic, and pragmatic dimensions. The findings indicate that although the systems generated broadly intelligible translations, they showed recurrent weaknesses in subject verb agreement, tense consistency, and especially pragmatic rendering, where idiomatic expressions posed substantial challenges. One system demonstrated comparatively stronger syntactic and semantic performance, yet none provided consistently adequate output without the need for substantial post editing. For comparative purposes, translations edited through a large-scale language model displayed improved grammatical correctness and reduced error rates, although occasional literal renderings required minor adjustments. The overall analysis suggests that current local technologies do not yet deliver dependable high quality translations independently and that significant technological refinement is required to enhance their usability for professional or high stakes applications.

Keywords: Artificial intelligence; language technology; machine translation; translation evaluation; translation quality.