用少量手写稿微调模型，能显著降低校对负担。
Practical Fine-Tuning of Autoregressive Models on Limited Handwritten Texts
- 仅需16行文本即可开始微调，逐步提升识别准确率。
- 256行时相对字符错误率降低40%，效果稳定可靠。
- 基于置信度选关键句子，可省一半标注工作量。
OCR应用中，用户上传文档并逐步修正自动识别结果，这一过程为模型持续适应提供了机会。我们证明，先进的基于Transformer的模型能有效支持这种渐进式微调，逐步减少人工校对工作量。实验表明，仅需16行文本即可启动微调，使字符错误率（CER）相对下降10%；当使用256行时，相对改进可达40%。我们还分析了模型各组件的作用，明确了编码器与解码器在微调中的分工。为此提出可靠的停止判断标准，涵盖直接指标与全局趋势分析。此外，通过基于置信度筛选有信息量的文本行，可将标注成本减半，同时保持相同性能。
原文摘要 · Abstract (English)
A common use case for OCR applications involves users uploading documents and progressively correcting automatic recognition to obtain the final transcript. This correction phase presents an opportunity for progressive adaptation of the OCR model, making it crucial to adapt early, while ensuring stability and reliability. We demonstrate that state-of-the-art transformer-based models can effectively support this adaptation, gradually reducing the annotator's workload. Our results show that fine-tuning can reliably start with just 16 lines, yielding a 10% relative improvement in CER, and scale up to 40% with 256 lines. We further investigate the impact of model components, clarifying the roles of the encoder and decoder in the fine-tuning process. To guide adaptation, we propose reliable stopping criteria, considering both direct approaches and global trend analysis. Additionally, we show that OCR models can be leveraged to cut annotation costs by half through confidence-based selection of informative lines, achieving the same performance with fewer annotations.
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。