引导大语言模型结合错误标注对机器翻译结果进行译后编辑
Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations
AI总结：
针对大语言模型尚未超越专用监督机器翻译系统的问题，提出引导LLaMA-2结合MQM质量反馈进行译后编辑的方法，经微调后在多语言翻译任务的自动与人工评估中均实现质量提升。
摘要：
机器翻译（MT）仍是大语言模型（LLMs）尚未取代专用监督系统的少数自然语言处理（NLP）任务之一。本研究利用LLMs与监督式MT的互补优势，引导LLMs借助从多维度质量指标（MQM）标注中提取的翻译质量外部反馈，自动对MT结果进行译后编辑。研究以LLaMA-2系列模型为基础，先探索了不同反馈类型的提示策略，随后对LLM进行微调以增强其利用给定引导信息的能力。在中译英、英译德、英译俄的MQM数据集上开展的实验表明，通过提示LLMs进行MT译后编辑可提升TER、BLEU和COMET分数，但细粒度反馈的增益尚不明确。微调则能更有效地整合细粒度反馈，在自动评估和人工评估中均进一步提升了翻译质量。
英文摘要：
Machine Translation (MT) remains one of the last NLP tasks where large language models (LLMs) have not yet replaced dedicated supervised systems. This work exploits the complementary strengths of LLMs and supervised MT by guiding LLMs to automatically post-edit MT with external feedback on its quality, derived from Multidimensional Quality Metric (MQM) annotations. Working with LLaMA-2 models, we consider prompting strategies varying the nature of feedback provided and then fine-tune the LLM to improve its ability to exploit the provided guidance. Through experiments on Chinese-English, English-German, and English-Russian MQM data, we demonstrate that prompting LLMs to post-edit MT improves TER, BLEU and COMET scores, although the benefits of fine-grained feedback are not clear. Fine-tuning helps integrate fine-grained feedback more effectively and further improves translation quality based on both automatic and human evaluation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
