Machine Translation Shifts on The Meaning Equivalence of Culture Sentence and Illocutionary Speech Acts: Back-Translation

ABSTRACT Machine translation, as an important tool in the field of artificial intelligence, has made significant progress in recent years. One of the most difficult aspects of machine translation is capturing the cultural nuances and meanings in illocutionary speech acts. Indonesian short story anthologies are an interesting example in this regard, as they contain distinctive and meaning-rich cultural terms. This study aims to explore the dynamic equivalence in machine translation shifts of sentences containing cultural terms and speech acts in Indonesian short story anthologies, as well as to evaluate the translation equivalence and success in transferring the cultural meaning. This study uses a descriptive qualitative research design with a content analysis approach. The analysis shows that the sentences in the short story anthology containing cultural terms and illocutionary speech acts experience translation shifts up to 83 data in the form of level and category shifts, which have an impact on the dynamic equivalence of translation. Google Translate can capture most of the cultural meanings, but there are still translation inequalities. Although machine translation technology such as Google Translate continues to evolve, further efforts are needed to capture cultural nuances and the ability to distinguish Arabic words without harakat (diacritical marks). Human involvement is still needed to ensure the accuracy of the translation results, especially in the cultural context and meaning of illocutionary speech acts. Keywords: Machine Translation, Cultural Terms, Short Story Anthology, Translation Shift, Dynamic Equivalence.