翻译的上下文精炼：用于句子和文档级后编辑的大型语言模型
Contextual Refinement of Translations: Large Language Models for Sentence and Document-Level Post-Editing
- Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
- SAP SE（思爱普公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出将大型语言模型作为自动后编辑而非直接翻译器，利用低秩适配器微调在句子和文档级翻译中取得显著改进，并在ContraPro测试集上达到89%的最先进准确率，同时利用人工修正减少后续编辑次数。
AI中文摘要：
大型语言模型（LLM）在各种自然语言处理任务中展现了显著的成功，但在神经机器翻译（NMT）中尚未达到最先进的性能。然而，它们在需要广泛理解和上下文处理的任务中的显著表现显示了其在翻译方面的潜力。为了利用这些能力，我们研究了将LLM用于机器翻译，并探索了最近的参数高效微调技术。令人惊讶的是，我们的初步实验发现，为翻译目的进行微调甚至导致了性能下降。为了克服这一点，我们提出了一种替代方法：将LLM适应为自动后编辑（APE）而非直接翻译器。基于LLM在处理和生成长序列方面的卓越能力，我们还提出将我们的方法扩展到文档级翻译。我们展示了利用低秩适配器微调进行APE可以在句子和文档级指标上产生显著改进，同时泛化到域外数据。最值得注意的是，我们在ContraPro测试集上达到了89%的最先进准确率，该测试集专门评估模型在从英语翻译到德语时解决代词歧义的能力。最后，我们研究了一个涉及文档级翻译的人工后编辑的实际场景，其中提供了参考上下文。在这里，我们展示了利用人工修正可以显著减少后续翻译所需的编辑次数（用于集成人工反馈的交互式演示可在此处找到：https://huggingface.co/spaces/skoneru/contextual_refinement_ende）。
英文摘要：
Large Language Models (LLM's) have demonstrated considerable success in various Natural Language Processing tasks, but they have yet to attain state-of-the-art performance in Neural Machine Translation (NMT). Nevertheless, their significant performance in tasks demanding a broad understanding and contextual processing shows their potential for translation. To exploit these abilities, we investigate using LLM's for MT and explore recent parameter-efficient fine-tuning techniques. Surprisingly, our initial experiments find that fine-tuning for translation purposes even led to performance degradation. To overcome this, we propose an alternative approach: adapting LLM's as Automatic Post-Editors (APE) rather than direct translators. Building on the LLM's exceptional ability to process and generate lengthy sequences, we also propose extending our approach to document-level translation. We show that leveraging Low-Rank-Adapter fine-tuning for APE can yield significant improvements across both sentence and document-level metrics while generalizing to out-of-domain data. Most notably, we achieve a state-of-the-art accuracy rate of 89\% on the ContraPro test set, which specifically assesses the model's ability to resolve pronoun ambiguities when translating from English to German. Lastly, we investigate a practical scenario involving manual post-editing for document-level translation, where reference context is made available. Here, we demonstrate that leveraging human corrections can significantly reduce the number of edits required for subsequent translations (Interactive Demo for integrating manual feedback can be found here: https://huggingface.co/spaces/skoneru/contextual_refinement_ende).
