Jun 2026· Dialogica· Vol 2, pp. 51-75· 1 citation· 10 references
TL;DR
It is argued that AI systems can produce linguistically plausible literary translations, but that poetic adequacy requires interpretive prioritisation, intercultural judgement, and aesthetic decision-making and contributes to research on AI-assisted literary translation by distinguishing surface fluency from poetic and intercultural adequacy.
Abstract
This article examines the quality of AI-generated poetry translation through a comparative study of Wilfred Owen’s Dulce et Decorum Est translated from English into Italian. The analysis compares Sergio Rufini’s published human translation with two AI-generated versions produced by ChatGPT and Google Translate. The study combines qualitative stanza-by-stanza close reading with a reduced Multidimensional Quality Metrics framework in order to assess both identifiable translation errors and broader losses of poetic, intercultural, and rhetorical force. The findings show that both AI-generated translations remain below the quality thresholds established in the MQM scorecard. ChatGPT produces a fluent and relatively coherent Italian version, but its output shows significant problems of undertranslation and poetic regularisation. Google Translate obtains a higher calibrated MQM score in this dataset, but its translation remains strongly oriented toward sentence-level transfer and does not consistently preserve the poem’s cumulative rhetorical structure. The article argues that AI systems can produce linguistically plausible literary translations, but that poetic adequacy requires interpretive prioritisation, intercultural judgement, and aesthetic decision-making. The study contributes to research on AI-assisted literary translation by distinguishing surface fluency from poetic and intercultural adequacy.
This critical narrative review synthesises evidence from ten recent publications in Scopus-indexed journals or conference proceedings, three directly relevant articles from Acta Humanitatis, DIALOGICA, and AI, and proposes a transparent protocol centred on identifiable texts, model and prompt documentation, repeated runs, preserved outputs, bilingual evaluation, linguistic evidence, negative cases, and explicit human responsibility.
The results show that LLMs and Google Translate consistently outperform specialized MT systems in terms of fluency, meaning preservation, and lexical-thematic alignment.
Beatriz Ribeiro Borges, P. H. R. Gabriel, E. Faria· International Journal of Dat...· 0 citations
The study finds that each prompt orientation produces distinct and observable shifts in diction, imagery construction and formal expression, and re-conceptualizes prompts not only as technical input instructions, but as purposive regulators of translation, offering a translation-theoretic framework for analysing LLM behaviour and practical guidance for designing Skopos-informed prompts for AI-assisted literary translation.
Haijin Li· Journal of Translation and L...· 0 citations
The rapid development of neural machine translation has transformed translation practices in academic and professional contexts. However, the ability of machine translation to preserve communicative functions within target texts remains debatable. This study compares the functional quality of Human Translation (HT) and Machine Translation (MT) using Christiane Nord's Functional Typology and functional adequacy framework, emphasizing communicative function, contextual sensitivity, and target-reader orientation as the main indicators of translation quality. A descriptive-comparative design with a mixed-methods approach was employed. Ten English academic texts categorized as informative texts were translated into Indonesian through both human and machine translation. Data were analyzed qualitatively using Nord's extratextual and intratextual factors and quantitatively through a scoring system of five indicators: text-function suitability, semantic accuracy, acceptability, contextual sensitivity, and cohesion-coherence. The findings reveal that Human Translation achieved a mean score of 19.0, categorized as highly adequate, while Machine Translation obtained a mean score of 13.2, categorized as moderately adequate. Human Translation demonstrated superior performance in maintaining academic register and communicative naturalness, whereas Machine Translation tended to produce literal structures with limited contextual adaptation. The novelty of this study lies in operationalizing Nord's functionalist framework into a measurable evaluation model for systematically comparing HT and MT. Functional evaluation proves more comprehensive than purely linguistic metrics in assessing translation quality in the AI-assisted translation era.
Dewi Rosnita, Hardiany, M. Rizqi et al.· Allure Journal· 0 citations
This study demonstrates that the primary challenge in translating Indonesian literary works into Arabic lies in the cultural elements embedded in metaphors, proverbs, and local expressions. Employing a qualitative textual analysis of Hamka’s Di Bawah Lindungan Kaʿbah, the research reveals that differences in worldview between Indonesian and Arab societies influence lexical choices and stylistic expressions, making literal translation insufficient. The findings highlight the necessity for translators to grasp the cultural context of the source text to ensure comprehensive meaning transfer. The study contributes to translation studies by formulating strategies that integrate semantic and stylistic approaches, including transliteration with explanatory notes, functional equivalence in the target culture, and the preservation of social metaphors. These strategies prove effective in maintaining cultural authenticity while ensuring readability for Arabic audiences. Overall, the research reinforces the view that literary translation is an act of intercultural mediation, synthesizing linguistic, semantic, and cultural dimensions to preserve meaning, aesthetic nuance, and cultural resonance in the target language.
It is argued that AI translation should not be understood solely as a technological tool but also as a transformative force redefining literary production, reception, and cross-cultural communication.
Nyiramukama Diana Kashaka· NEWPORT INTERNATIONAL JOURNA...· 0 citations