arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.01017cs.CVcs.LG
收藏

TableFormer:使用Transformers理解表结构

TableFormer: Table Structure Understanding with Transformers

IBM Research(IBM研究院)

Ahmed Nassar, Nikolaos Livathinos, Maksym Lysak, Peter Staar

摘要:

表格以简洁紧凑的方式组织有价值的内容。这些内容对于诸如搜索引擎、知识图谱等系统是非常有价值的,因为它们增强了它们的预测能力。不幸的是,桌子有各种各样的形状和大小。此外,它们可能具有复杂的列/行标题配置、多行、不同种类的分隔线、缺失条目等。因此,从图像中正确识别表结构是一项重要的任务。本文提出了一种新的表结构辨识模型。后者以两种重要的方式改进了最新的端到端深度学习模型(即来自PubTabNet的编码器-双解码器)。首先,我们介绍了一种新的目标检测解码器的表格单元格。通过这种方式,我们可以直接从PDF源获得可编程PDF的表格单元格的内容,并避免自定义OCR解码器的训练。这种架构上的变化导致了更准确的表格内容提取,并允许我们处理非英语表格。其次,我们用基于Transformer的解码器替换LSTM解码器。这一升级显著提高了以前最先进的树编辑距离分数(TEDS),在简单表上从91%提高到98.5%,在复杂表上从88.7%提高到95%。

英文摘要:

Tables organize valuable content in a concise and compact representation. This content is extremely valuable for systems such as search engines, Knowledge Graph's, etc, since they enhance their predictive capabilities. Unfortunately, tables come in a large variety of shapes and sizes. Furthermore, they can have complex column/row-header configurations, multiline rows, different variety of separation lines, missing entries, etc. As such, the correct identification of the table-structure from an image is a non-trivial task. In this paper, we present a new table-structure identification model. The latter improves the latest end-to-end deep learning model (i.e. encoder-dual-decoder from PubTabNet) in two significant ways. First, we introduce a new object detection decoder for table-cells. In this way, we can obtain the content of the table-cells from programmatic PDF's directly from the PDF source and avoid the training of the custom OCR decoders. This architectural change leads to more accurate table-content extraction and allows us to tackle non-english tables. Second, we replace the LSTM decoders with transformer based decoders. This upgrade improves significantly the previous state-of-the-art tree-editing-distance-score (TEDS) from 91% to 98.5% on simple tables and from 88.7% to 95% on complex tables.

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。

↑