Machine Translation of Selected Ghazals of Hafiz from Persian into English

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation with the potential to overcome many weaknesses in conventional phrase-based systems. However, there are still grey areas that need attention field of machine translation, mainly context literary and poetic language. This research aims identify shortcomings NMT addressing ambiguity semantic complexities expressions important translating literature a cross-cultural multilingual context. Furthermore, while human translators struggle retain naturalness accuracy this what extent could convey message literary-based texts from Persian into English. The corpus study consists Forty ghazals Divan Hafiz, which translated by computer-assisted software, memoQ then compared authentic Hafiz Henry Wilberforce Clarke. comparative descriptive portrayed challenges issues related Hafiz’s poems, demonstrate touch lost MT products.