无需标注数据，跨语言识别表格结构，准确率提升11.12%
SPRINT: Script-agnostic Structure Recognition in Tables
- 用OTSL序列预测单元格布局，不依赖语言
- 非英语表格结构识别准确率提升11.12%
- 支持13种语言、多种文字，适合多语言文档处理
表格结构识别（TSR）对信息检索、表格重建和文档理解等任务至关重要。尽管当前最先进的方法主要针对英文文档，但全球数据多样性要求跨语言能力。在非英文语境下构建大规模标注数据并从头训练模型成本高昂。本文提出一种语言无关的单元格排列预测方法，命名为SPRINT。它利用最近提出的优化表格结构语言（OTSL）序列来预测表格结构，并结合预训练的表格网格估计器，在非英文文档上显著提升树编辑距离相似度得分。在PubTabNet、FinTabNet和PubTables-1M等基准数据集上的实验表明，SPRINT在标准数据集上性能媲美现有最优模型，同时具有更低延迟。尤其在非英文文档中，其平均准确率绝对提升11.12%。我们还提出将有效OTSL预测转换为通用HTML表格表示的算法。为推动研究，我们在GitHub发布代码及多语言扫描与场景表格结构识别数据集MUSTARD，包含1428张跨13种语言、多种文字的表格，均以OTSL标注。
原文摘要 · Abstract (English)
Table Structure Recognition (TSR) is vital for various downstream tasks like information retrieval, table reconstruction, and document understanding. While most state-of-the-art (SOTA) research predominantly focuses on TSR in English documents, the need for similar capabilities in other languages is evident, considering the global diversity of data. Moreover, creating substantial labeled data in non-English languages and training these SOTA models from scratch is costly and time-consuming. We propose TSR as a language-agnostic cell arrangement prediction and introduce SPRINT, Script-agnostic Structure Recognition in Tables. SPRINT uses recently introduced Optimized Table Structure Language (OTSL) sequences to predict table structures. We show that when coupled with a pre-trained table grid estimator, SPRINT can improve the overall tree edit distance-based similarity structure scores of tables even for non-English documents. We experimentally evaluate our performance across benchmark TSR datasets including PubTabNet, FinTabNet, and PubTables-1M. Our findings reveal that SPRINT not only matches SOTA models in performance on standard datasets but also demonstrates lower latency. Additionally, SPRINT excels in accurately identifying table structures in non-English documents, surpassing current leading models by showing an absolute average increase of 11.12%. We also present an algorithm for converting valid OTSL predictions into a widely used HTML-based table representation. To encourage further research, we release our code and Multilingual Scanned and Scene Table Structure Recognition Dataset, MUSTARD labeled with OTSL sequences for 1428 tables in thirteen languages encompassing several scripts at https://github.com/IITB-LEAP-OCR/SPRINT
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。