EUREKAEUREKA

IJOLEH : International Journal of Education and HumanitiesIJOLEH : International Journal of Education and Humanities

The research aims to analyze the fidelity of Google Translate, DeepL Translate, and Libre Translate in conveying the meaning and intent of the poetry. Employing a mixed-method approach, data were collected from ten purposively selected lecturers at Universitas Islam Makassar and Universitas Megarezky Makassar. Quantitative data were obtained through a structured questionnaire using a five-point Likert scale to measure fidelity, while qualitative insights were gathered via thematic content analysis of the AI-powered poetry translations. Findings reveal a clear fidelity score: DeepL Translate (mean = 4.5, excellent), Google Translate (mean = 3.7, good), and Libre Translate (mean = 1.8, low). The researcher concludes that AI-powered translation tools exhibit considerable variability in their capacity to maintain the message, intent, and stylistic attributes of poetry. Of the three systems assessed, DeepL Translate shows the highest level of fidelity, supported by both quantitative evaluations and qualitative theme analyses.

The research concludes that DeepL Translate offers the best and most natural translations of poetry, followed by Google Translate and Libre Translate.All three tools could convey the main idea, but often lost the poems beauty, rhythm, and emotion, illustrating that AI translation still struggles with creative or artistic language.AI translation systems should be used to assist student learning, not to replace human translators, and developers should focus on improving AIs understanding of metaphorical language, emotion, and style in poetry.

Penelitian lebih lanjut perlu dilakukan untuk mengeksplorasi bagaimana AI dapat ditingkatkan dalam menangkap nuansa emosional dan gaya bahasa yang khas dalam puisi. Hal ini dapat dilakukan dengan mengembangkan model AI yang dilatih khusus pada korpus puisi yang besar dan beragam, serta dengan menggabungkan teknik pemrosesan bahasa alami yang lebih canggih. Selain itu, penelitian dapat difokuskan pada pengembangan metrik evaluasi yang lebih komprehensif untuk mengukur kualitas terjemahan puisi, yang tidak hanya mempertimbangkan akurasi semantik tetapi juga aspek estetika dan artistik. Terakhir, penting untuk meneliti bagaimana penggunaan alat terjemahan AI memengaruhi persepsi dan interpretasi pembaca terhadap puisi, serta bagaimana hal ini dapat dimanfaatkan untuk meningkatkan pengalaman belajar dan apresiasi sastra.

  1. ASSESSMENT OF HUMAN TRANSLATION VS. AI TRANSLATION IN A LITERARY WORK | VNU Journal of Foreign Studies.... doi.org/10.63023/2525-2445/jfs.ulis.5513ASSESSMENT OF HUMAN TRANSLATION VS AI TRANSLATION IN A LITERARY WORK VNU Journal of Foreign Studies doi 10 63023 2525 2445 jfs ulis 5513
  2. [2310.20326] Erato: Automatizing Poetry Evaluation. erato automatizing poetry evaluation computer science... doi.org/10.48550/arXiv.2310.203262310 20326 Erato Automatizing Poetry Evaluation erato automatizing poetry evaluation computer science doi 10 48550 arXiv 2310 20326
  3. Fidelity Analysis of Artificial Intelligence-Powered Poetry Translation: A Comparison of Google Translate,... jurnal-eureka.com/index.php/ijoleh/article/view/422Fidelity Analysis of Artificial Intelligence Powered Poetry Translation A Comparison of Google Translate jurnal eureka index php ijoleh article view 422
  4. Translation Techniques in Literary Poetry Texts: A Systematic Literature Review | Indonesian Journal... doi.org/10.58835/ijtte.v4i2.406Translation Techniques in Literary Poetry Texts A Systematic Literature Review Indonesian Journal doi 10 58835 ijtte v4i2 406
Read online
File size584.19 KB
Pages10
DMCAReport

Related /

ads-block-test