人工智能辅助文化遗产传播：比较NMT和术语增强大语言模型在岩画文档中的翻译
AI-assisted cultural heritage dissemination: Comparing NMT and glossary-augmented LLM translation in rock art documents
AI总结：
本文比较了NMT和术语增强大语言模型在岩画文档翻译中的表现，发现术语增强方法在术语准确性上更优，且在保持整体质量方面表现良好。
摘要：
文化机构在全球范围内越来越多地发布研究和解释材料，但多语言传播受到预算和人力限制的制约。在术语密集的领域如岩画中，翻译质量依赖于准确且一致的专业术语，小的词汇错误可能误导非专业人士并降低再利用率。我们比较了三种英语机器翻译设置，专注于简单、操作可行的干预措施而非复杂的模型侧修改：(1) DeepL作为强大的NMT基线，(2) Gemini-Simple（带有基本提示的LLM），以及(3) Gemini-RAG（相同的LLM通过术语对检索增强提示）。使用PEARMUT，我们通过(i)多向直接评估（0-100）和(ii)带有受限MQM分类法的定向术语审计进行人工评估。Gemini-RAG在精确匹配术语准确性上最高（81.4%），相比Gemini-Simple（69.1%）和DeepL（64.4%），同时保持整体质量（平均DA 85.3 Gemini-RAG vs. 85.2 Gemini-Simple），优于DeepL（80.3%）。这些结果表明，如果机构维护最少的术语资源和轻量级评估程序，术语增强提示是一种低开销的方法，可以提高文化遗产翻译中的术语控制。
英文摘要：
Cultural heritage institutions increasingly disseminate research and interpretive materials globally, but multilingual dissemination is constrained by limited budgets and staffing. In terminology-dense domains such as rock art, translation quality depends on accurate, consistent specialised terms, and small lexical errors can mislead non-specialists and reduce reuse. We compare three English MT setups for a Spanish academic rock art text, focusing on simple, operationally feasible interventions rather than complex model-side modifications: (1) DeepL as a strong NMT baseline, (2) Gemini-Simple (LLM with a basic prompt), and (3) Gemini-RAG (the same LLM with glossary-augmented prompting via term-pair retrieval). Using PEARMUT, we conduct a human evaluation via (i) multi-way Direct Assessment (0--100) and (ii) targeted terminology auditing with a restricted MQM taxonomy. Gemini-RAG yields the highest exact-match terminology accuracy (81.4\%), versus Gemini-Simple (69.1\%) and DeepL (64.4\%), while preserving overall quality (mean DA 85.3 Gemini-RAG vs. 85.2 Gemini-Simple), outperforming DeepL (80.3). These results show that glossary-augmented prompting is a low-overhead way to improve terminology control in cultural-heritage translation if institutions maintain minimal terminology resources and lightweight evaluation procedures.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
