用机器翻译把英文道德语料转成波兰语，效果仍可用于跨语言道德分析。
Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corpora
- 用四种方法验证直接翻译能否保留道德细微差别
- 翻译后道德分类准确率差距仅0.01–0.02 AUROC，相似度达0.89
- 适合想低成本拓展非英语语言道德研究的学者
道德语言微妙且具文化差异，跨语言翻译常引入偏差。尽管自动化道德价值分类依赖大量英文标注语料，我们以波兰语为案例，测试大模型翻译是否可弥合这一鸿沟。基于约5万条涵盖多元话题的道德标注社交媒体文本，采用四阶段验证流程：LaBSE跨语言嵌入相似性、中心核对齐（CKA）、LLM作为评判者评估及深度学习分类器一致性检验。结果表明，尽管在俚语、粗俗表达和文化负载词上存在不足，直接翻译仍能较好保留微妙道德线索，使跨语言机器学习有效——平均余弦相似度达0.89，各道德基础分类准确率差距仅为0.01–0.02 AUROC。研究证明，机器翻译是当前资源匮乏语言中开展道德研究的可行且经济路径，并可推广至其他斯拉夫语系语言。
原文摘要 · Abstract (English)
Moral language is subtle and culturally variable, making it difficult to translate faithfully across languages. Idiomatic expressions, slang, and cultural references introduce hard-to-avoid translation artefacts. Yet automated moral values classification depends on language-specific annotated corpora that exist almost exclusively in English. We investigate whether LLM-based translation can bridge this gap, taking Polish as a test case. Using $\sim~50k$ morally-annotated social media posts from a diverse range of topics, we apply a principled four-method validation pipeline: LaBSE cross-lingual embedding similarity, Centered Kernel Alignment (CKA), LLM-as-judge evaluation, and deep learning classifier parity tests. We show that despite shortcomings in handling slang, vulgarity, and culturally-loaded expressions, direct translation preserves subtle moral cues well enough to be harvested by cross-lingual machine learning - with a mean cosine similarity of 0.89 and classification accuracy gaps of 0.01--0.02 AUROC across foundations. These results demonstrate that machine translation is a practical and cost-effective path to moral values research in languages currently under-resourced in this domain. We demonstrate this for Polish as a representative Slavic language, with expected generalization to related languages.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。