Machine translation systems and quality assessment: a systematic review

Abstract Nowadays, in the globalised context which we find ourselves, language barriers can still be an obstacle to accessing information. On occasions, it is impossible satisfy demand for translation by relying only human translators, therefore, tools such as Machine Translation (MT) are gaining popularity due their potential overcome this problem. Consequently, research field constantly growing and new MT paradigms emerging. In paper, a systematic literature review has been carried out order identify what systems currently most employed, architecture, quality assessment procedures applied determine how they work, of these offer best results. The study focused on specialised produced experts, linguists, specialists related fields that include English–Spanish combination. Research findings show neural predominant paradigm current scenario, being Google Translator used system. Moreover, analysed works one type evaluation—either automatic or human—to assess machine 22% combined two types evaluation. However, more than half included error classification analysis, essential aspect identifying flaws improving performance systems.