量化评估翻译模型注意力的可解释性，找出发散度与翻译质量的关系。
Advancing Explainability in Neural Machine Translation: Analytical Metrics for Attention and Alignment Consistency
- 用注意力熵和对齐一致率衡量注意力模式可解释性。
- 更集中的注意力分布提升可解释性，但不保证翻译质量更好。
- 适合关注模型可信度与透明性的研究者参考。
神经机器翻译（NMT）模型虽表现优异，但其决策过程仍不透明。本文提出系统性框架，通过对比统计对齐并关联标准翻译质量指标，量化评估NMT模型注意力模式的可解释性。引入注意力熵与对齐一致率两个指标，在WMT14英文-德文测试子集上使用预训练mT5模型进行验证。结果表明，更尖锐的注意力分布有助于提升可解释性，但并不总能带来更好的翻译质量。该研究深化了对NMT可解释性的理解，为构建更透明、可靠的翻译系统提供指导。
原文摘要 · Abstract (English)
Neural Machine Translation (NMT) models have shown remarkable performance but remain largely opaque in their decision making processes. The interpretability of these models, especially their internal attention mechanisms, is critical for building trust and verifying that these systems behave as intended. In this work, we introduce a systematic framework to quantitatively evaluate the explainability of an NMT model attention patterns by comparing them against statistical alignments and correlating them with standard machine translation quality metrics. We present a set of metrics attention entropy and alignment agreement and validate them on an English-German test subset from WMT14 using a pre trained mT5 model. Our results indicate that sharper attention distributions correlate with improved interpretability but do not always guarantee better translation quality. These findings advance our understanding of NMT explainability and guide future efforts toward building more transparent and reliable machine translation systems.
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。