透過格式強化學習實現結構化文件翻譯

摘要

近期關於結構化文本翻譯的研究仍侷限於句子層級，因其難以有效處理複雜的文件級XML或HTML結構。為解決此問題，我們提出格式強化學習（FormatRL），該方法在監督式微調模型基礎上採用群組相對策略優化，直接針對兩種新型結構感知獎勵函數進行優化：1) TreeSim——衡量預測XML樹與參考XML樹的結構相似度；2) Node-chrF——在XML節點層級評估翻譯品質。此外，我們採用能區分輕微錯誤與嚴重結構失誤的細粒度指標StrucAUC。在SAP軟體文件基準測試中的實驗表明，該方法在六項指標上均有提升，進一步分析揭示了不同獎勵函數如何共同促進結構完整性與翻譯品質的改善。

English

Recent works on structured text translation remain limited to the sentence level, as they struggle to effectively handle the complex document-level XML or HTML structures. To address this, we propose Format Reinforcement Learning (FormatRL), which employs Group Relative Policy Optimization on top of a supervised fine-tuning model to directly optimize novel structure-aware rewards: 1) TreeSim, which measures structural similarity between predicted and reference XML trees and 2) Node-chrF, which measures translation quality at the level of XML nodes. Additionally, we apply StrucAUC, a fine-grained metric distinguishing between minor errors and major structural failures. Experiments on the SAP software-documentation benchmark demonstrate improvements across six metrics and an analysis further shows how different reward functions contribute to improvements in both structural and translation quality.

透過格式強化學習實現結構化文件翻譯

Structured Document Translation via Format Reinforcement Learning

摘要

Support