发表机构
AI-Bio Convergence Research Inst.; Soongsil University（AI-生物融合研究所; 崇实大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FACET 是一种无参考的翻译质量评估方法，通过流畅性、准确性和一致性三个环节分解评估，仅使用固定模型提示三次，无需训练组件，在 WMT26 任务中排名后编辑人工翻译第一，一致性环节对分数影响小。
AI 中文摘要
机器翻译中的不同错误类型需要不同的证据。意义是否得到保留只能根据源文本来判断，而目标文本是否结构良好，或者是否一致地命名某个实体，则可以仅根据目标文本来判断。我们提出了 FACET，这是我们提交给 WMT26 自动翻译质量评估任务的无参考系统，它将评估分解为流畅性、准确性和一致性三个环节，并且每个环节只获得其错误类型所需的上下文。一个固定的模型被提示三次，合并后的错误跨度产生三个任务输出：错误跨度、质量分数和无错误标签，且不包含任何训练组件。我们还提交了 FACET-C，它省略了一致性环节。在没有黄金标签的情况下，我们描述了 FACET 的预测特征。其系统排名将后编辑的人工翻译排在首位，而一致性环节改变了约十分之一的片段分数，同时几乎不改变排名。
英文摘要
Different error types in machine translation require different evidence. Whether meaning is preserved can be judged only against the source, while whether the target is well-formed, or whether it names one entity consistently, can be judged from the target alone. We present FACET, our reference-free submission to the WMT26 Automated Translation Quality Evaluation Task, which decomposes evaluation into Fluency, Accuracy, and Consistency passes and gives each pass only the context its error type requires. A single fixed model is prompted three times, and the merged error spans yield the three task outputs, error spans, quality scores, and error-free labels, with no trained components. We also submit FACET-C, which omits the Consistency pass. Without gold labels, we characterize the predictions of FACET. Its system rankings place post-edited human translation first, and the Consistency pass changes about a tenth of segment scores while leaving the ranking nearly unchanged.
CommentsAccepted at WMT 2026 (shared task system paper)
