用大模型自动生成标注，无需人工就能提升机器翻译错误定位效果。
Is Human Annotation Necessary? Iterative MBR Distillation for Error Span Detection in Machine Translation
- 用大模型生成伪标签，通过迭代MBR蒸馏训练模型
- 在系统级和片段级上超越人工标注的监督模型
- 适合资源有限但需高精度错误检测的场景
错误片段检测（ESD）是机器翻译评估中的关键任务，旨在识别翻译错误的位置与严重程度。尽管微调模型在人工标注数据上能提升性能，但获取此类数据成本高且存在标注者间不一致问题。为此，我们提出一种基于最小贝叶斯风险（MBR）解码的自进化框架——迭代MBR蒸馏（Iterative MBR Distillation for ESD），通过使用现成的大语言模型生成伪标签，彻底消除对人工标注的依赖。在WMT Metrics Shared Task数据集上的大量实验表明，仅使用这些自生成伪标签训练的模型，在系统级和片段级均优于未适配的基础模型以及基于人工标注训练的监督基线，同时在句子级保持了有竞争力的性能。
原文摘要 · Abstract (English)
Error Span Detection (ESD) is a crucial subtask in Machine Translation (MT) evaluation, aiming to identify the location and severity of translation errors. While fine-tuning models on human-annotated data improves ESD performance, acquiring such data is expensive and prone to inconsistencies among annotators. To address this, we propose a novel self-evolution framework based on Minimum Bayes Risk (MBR) decoding, named Iterative MBR Distillation for ESD, which eliminates the reliance on human annotations by leveraging an off-the-shelf LLM to generate pseudo-labels. Extensive experiments on the WMT Metrics Shared Task datasets demonstrate that models trained solely on these self-generated pseudo-labels outperform both unadapted base model and supervised baselines trained on human annotations at the system and span levels, while maintaining competitive sentence-level performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。