Translation Errors and Post-editing Strategies in ChatGPT-assisted Translation of Chinese Political Texts: A Case Study of The Report on China’s Right to Development
May 2026· International Journal of English Literature and Social Sciences· Vol 11, pp. 573-577· 0 citations· 10 references
Abstract
Large language models are increasingly being incorporated into translation workflows, yet their performance in politically sensitive texts remains underexplored. Political discourse poses particular challenges for machine translation because it relies heavily on specialized terminology, ideological meanings, and context-dependent expressions. Drawing on Chapter Three of The Report on China’s Right to Development, this paper examines translation errors in ChatGPT-generated output through a comparison with revised human translations. The analysis identifies three recurring problem areas: unnatural linguistic choices, weak information organization, and non-standard rendering of political terms. These problems are traced to limitations in probabilistic text generation, insufficient domain-specific knowledge, and incomplete contextual interpretation. To address them, three post-editing strategies are proposed: register adjustment, structural reorganization, and terminology standardization. The findings suggest that while ChatGPT is capable of producing fluent drafts, high-quality translation of political texts still depends on human expertise. The study highlights the continuing importance of post-editing in ensuring linguistic accuracy, conceptual precision, and discourse appropriateness in AI-assisted political translation.
As China-focused narratives increasingly enter international circulation, Chinese-to-English translation has become a site of meaning negotiation rather than a straightforward linguistic transfer. For student translators, the primary challenge extends beyond lexical selection; it involves deciding how to render culturally saturated references, evaluative stances, and narrative positioning for readers outside the source context. This study examines the real-time decision-making and revision behaviors of 72 English majors translating China-focused narratives. Using a process-product design, the research integrates keystroke-logging data collected with Translog-II, translation product evaluations, and an auxiliary danmu (time-synced commentary) corpus treated as an audience-salience layer rather than as a direct measure of segment-level linguistic difficulty. Translation processes were analyzed across pause duration, revision frequency, revision location, and stage distribution, while product quality was assessed through expert rating and targeted coding of culture-related segments. A corpus of 18,642 danmu comments from 24 Bilibili videos was used to identify publicly salient narrative themes and culturally sensitive expressions. Results show that culture-loaded and evaluatively dense segments triggered longer pauses, increased recursive revisions, and denser mid-process reformulations. Higher-quality translations were associated with selective, strategically timed revisions at the discourse and cultural-adaptation levels rather than with a higher total revision count. The overlap between danmu-salient narrative triggers and high-effort translation segments is interpreted as convergent evidence of audience salience and translator processing pressure, not as evidence of causation. The study advances research on the translation process by linking revision behavior to culturally embedded narrative translation and offering implications for translator training in cross-cultural communication.
Unknown authors· Journal of Visualized Experi...· 0 citations
Large language models (LLMs) such as ChatGPT have advanced machine translation, but their quality on low-resource language pairs remains uneven and is typically assessed with automatic metrics alone. This study examines how prompting strategy and source-text type jointly affect LLM translation quality for the low-resource Chinese–Vietnamese pair and whether automatic and human assessments agree. Using a 2 × 3 mixed factorial design, we compared an English-mediated pivot strategy with a direct strategy across informative, expressive, and operative texts, evaluating 60 ChatGPT translations with COMET and with 15 bilingual readers who rated adequacy, fluency, faithfulness, trustworthiness, willingness to use, and need for revision. On COMET, pivoting significantly improved overall quality (p < 0.001), text type was the dominant factor (η2 = 0.91; informative > operative > expressive), and strategy interacted with text type, with the largest pivot gain for expressive texts. Human ratings reproduced this ordering but diverged sharply for expressive texts: although COMET favoured the pivot output, readers reported that pivoting raised fluency yet substantially reduced faithfulness (4.10 → 1.77 on a 7-point scale) and were unwilling to accept it. These results show that the value of a prompting strategy is text-type-dependent and that fluent LLM output is not necessarily faithful, underscoring the need to pair automatic metrics with human evaluation when benchmarking low-resource translation.
General-text translation is converging toward near-full automation by large language models (LLMs), yet the translation of OTT multimedia content still demands a deliberately designed division of labor between humans and AI; this asymmetry is the starting point of this review. Korea occupies a distinctive position in this transformation: the global success of Korean content has created an asymmetric, outbound-heavy translation market in which linguistically complex Korean-source material must be localized into dozens of languages at speed, while the domestic language-service industry undergoes a structural shift from human translation to machine-translation post-editing. This paper reviews three research streams that have developed largely in isolation, namely LLM translation quality and automatic evaluation, human–AI collaboration and knowledge-worker productivity, and audiovisual translation, and integrates them through an operations-management input–process–output–outcome framework tailored to the Korean OTT context. The review finds that LLM-based post-editing improves draft quality and productivity, but that honorific register, culture-bound expressions, and speaker-relational meaning, all pervasive in Korean dialogue, lie largely outside current LLM competence. Three testable propositions are derived on how Korean-specific linguistic density conditions the productivity–quality trade-off, and a research agenda is proposed with implications for job redesign and capability development in language service providers, OTT platforms, and language-focused higher education. Designing this division of labor is a management problem before it is a technological one, and its answers lie where language expertise and operations management meet.
The integration of machine translation (MT) and artificial intelligence into translation workflows has significantly transformed professional practice, particularly in high-stakes domains such as medical translation. This study investigates professional translators’ perspectives on post-editing (PE) and translation quality assessment (TQA) in English–Romanian medical translation. Drawing on structured interviews and thematic analysis, the findings indicate that MT is primarily used as a support tool due to persistent issues related to terminology and contextual accuracy. Post-editing is considered essential, though often applied without structured adherence to standards such as ISO 18587, while TQA models are unevenly implemented in practice. The study also identifies a significant gap between academic training and professional requirements, particularly regarding technological and domain-specific competences. These findings highlight the need for a more integrated and practice-oriented approach to translator training in the Romanian context.
Z. Kovács, Daniel Dejica· Scientific Bulletin of the P...· 0 citations
It is suggested that LLM agents can reach a strong MT baseline and may offer pragmatic and audience-oriented affordances, while their value depends on the benchmark system, the target discourse function, and the evaluation dimension.
It is argued that NLP becomes most valuable for the Iraqi humanities when computational methods are combined with cultural knowledge, philological care, translation ethics, and close literary interpretation.
Tetyana Panyok· Iraqi Literary and Cultural...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
