基于模型的大规模多语言平行数据质量评估

摘要

大规模多语言双语语料通常包含两个不同问题：非平行句对和低质量翻译。我们将对此类数据的基于模型评估分解为两个独立组件：基于多语言嵌入的平行度评估和无参考质量估计。针对平行度评估，我们在FLORES-200和BOUQuET检索任务上对四种嵌入模型进行基准测试，涵盖目标语言对清单中的6,654个源语—目标语方向。针对质量估计，我们在专业的FLORES-200翻译上，跨越41,412个有序的源语—目标语方向，评估了九种无参考评估器。结果表明，没有任何模型能在所有翻译方向上表现可靠。简单的质量估计集成会稀释强模型信号，而有记录的目标语言覆盖范围与更高的质量估计分数密切相关。总体而言，这些发现表明，多语言平行数据评估最好被视为一个方向感知的路由与校准问题，因为预计没有单一的通用指标能够适用于所有语言。

English

Large-scale multilingual bitext often contains two distinct problems: non-parallel sentence pairs and low-quality translations. We decompose model-based assessment for such data into two independent components: parallelism assessment with multilingual embeddings and reference-free quality estimation (QE). For parallelism, we benchmark four embedding models on FLORES-200 and BOUQuET retrieval tasks, covering 6,654 source--target directions in our target language-pair inventory. For QE, we evaluate nine reference-free evaluators on professional FLORES-200 translations across 41,412 ordered source--target directions. Results show that no model is universally reliable across translation directions. Naive QE ensembles dilute strong model signals, while documented target-language coverage is strongly associated with higher QE scores. Overall, these findings suggest that multilingual parallel-data assessment is best approached as a direction-aware routing and calibration problem, where no single universal metric is expected to suffice across all languages.