Bridging Sentence and Document Contexts: A PEFT-Enhanced Framework for Document-Level Neural Machine Translation

Document-level neural machine translation (DNMT) faces challenges in integrating context and maintaining semantic consistency. This paper proposes a coarse-to-fine semantic transfer approach that captures both fine-grained and coarse-grained document-level context. By employing a two-stage training strategy with Adapter-enhanced modules, the method ensures effective semantic adaptation from sentence to document levels. Experiments on three datasets demonstrate significant improvements in s-BLEU and d-BLEU metrics, outperforming existing approaches.