Tradução automática e poesia: o caso do inglês e do português

Abstract

This article sets out to analyse the translations into Portuguese of three poems written I English, “A Letter is a Joy of Earth” by Emily Dickinson, “To a Stranger” by Walt Whitman and “Sandra” by Charles Bukowski. Three translations by three human translators, Geir Campos, Pedro Gonzaga and Jorge de Sena, are compared to the translations made by Google Translate in order to evaluate machine translation quality. This research shows that machine translations are less “ludicrous” than some would think and are in fact quite acceptable. In the cases investigated, machine translations are sometimes as acceptable as the ones made by the professional translators, and they could even help them to make mistakes through a lack of attention or by ignoring all the possibilities in the case of polysemous words. The Google translations are obviously plainer and there are a number of mistakes in them of the kind one expects: wrong concordances, wrong interpretations of polysemous words, wrong interpretation of gendered words. However, overall the results are far more satisfying than forecast. Google Translate, or similar programmes, may help translators with different, albeit sound alternatives. Additionally, machine translations provide a useful tool to analyse the idiosyncrasies of translators.

AI-translated poetry: Ivan Franko's poems in GPT-3.5-driven machine and human-produced translations

“…Dai et al (2022) discussed the limitations of machine translation for poetry, citing its struggle to convey the beauty of ancient Chinese traditional culture while noting the occasional enrichment of language through figures of speech. Humblé (2019) found Google Translate's translations of E. Dickinson's poems into Portuguese to be surprisingly satisfactory. In 2023, Alowedi and Al-Ahdal (2023) conducted a linguistic analysis comparing Arabic poem translations, concluding that machine translation falls short in capturing nuances and cultural context, advocating for machineassisted translation with post-editing as a cost-effective solution.…”

“…In this era of remarkable advancements in artificial intelligence striving to emulate and potentially surpass human translators, significant progress has been made in the efficacy, speed, and accuracy of machine translation. Key developments include Google Translate's proficient translations of Portuguese poetry into English Humblé (2019), and the notable shift in AI machine translation evaluations, transitioning from "satisfactory" to being recognized as a "clear success" as per Poibeau (2022). However, the translation of poetry remains a largely uncharted frontier and poses a formidable challenge for machine translation 2.…”