用质量评估提升表格提取效果，让无标注数据更有效。
QUEST: Quality-aware Semi-supervised Table Extraction for Business Documents
- 引入质量评估模型预测F1分数，指导伪标签选择。
- 在私有数据集上F1提升至74%（原64%），空预测减少45%。
- 适合标注少、对结构完整要求高的企业文档场景。
从企业文档中自动化提取表格对工业流程至关重要，但受限于标注稀疏和多阶段流水线易出错。现有半监督学习方法依赖置信度评分，无法准确反映提取质量。本文提出QUEST框架，通过训练质量评估模型，结合结构与上下文特征预测F1分数，而非依赖置信度。该质量感知机制在迭代半监督训练中指导伪标签选择，同时使用多样性度量（DPP、Vendi得分、IntDiv）缓解确认偏差。在自有企业数据集（1000个标注+10000个未标注文档）上，F1从64%提升至74%，空预测率下降45%（从12%降至6.5%）。在DocILE基准（600个标注+20000个未标注文档）上，F1达50%（原42%），空预测率减少19%（从27%降至22%）。框架具备可解释的质量评估和对标注稀缺的鲁棒性，特别适用于对结构一致性与数据完整性要求高的企业文档场景。
原文摘要 · Abstract (English)
Automating table extraction (TE) from business documents is critical for industrial workflows but remains challenging due to sparse annotations and error-prone multi-stage pipelines. While semi-supervised learning (SSL) can leverage unlabeled data, existing methods rely on confidence scores that poorly reflect extraction quality. We propose QUEST, a Quality-aware Semi-supervised Table extraction framework designed for business documents. QUEST introduces a novel quality assessment model that evaluates structural and contextual features of extracted tables, trained to predict F1 scores instead of relying on confidence metrics. This quality-aware approach guides pseudo-label selection during iterative SSL training, while diversity measures (DPP, Vendi score, IntDiv) mitigate confirmation bias. Experiments on a proprietary business dataset (1000 annotated + 10000 unannotated documents) show QUEST improves F1 from 64% to 74% and reduces empty predictions by 45% (from 12% to 6.5%). On the DocILE benchmark (600 annotated + 20000 unannotated documents), QUEST achieves a 50% F1 score (up from 42%) and reduces empty predictions by 19% (from 27% to 22%). The framework's interpretable quality assessments and robustness to annotation scarcity make it particularly suited for business documents, where structural consistency and data completeness are paramount.
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。