Advancing Explainability in Neural Machine Translation: Analytical Metrics for Attention and Alignment Consistency
This work addresses the need for more transparent and reliable machine translation systems, though it is incremental in nature.
The paper tackled the problem of evaluating explainability in neural machine translation by introducing metrics for attention and alignment consistency, finding that sharper attention distributions correlate with improved interpretability but not always with better translation quality.
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.