Form-NLU：面向表单自然语言理解的数据集
Form-NLU: Dataset for the Form Natural Language Understanding
AI总结：
本文提出首个用于表单结构理解与键值提取的数据集 Form-NLU，并构建了基于位置和逻辑关系的提取框架，通过实验验证了其方法在真实场景中的有效性。
摘要：
与一般文档分析任务相比，表单文档结构理解与检索更具挑战性。表单文档通常由两类作者制作：表单设计者负责开发表单结构和键，表单用户根据提供的键填写表单值。因此，如果表单用户产生混淆，表单值可能与表单设计者的意图（结构和键）不一致。本文介绍 Form-NLU，这是首个用于表单结构理解及其键值信息提取的新颖数据集，旨在解释表单设计者的意图以及用户填写值与其的对齐情况。它包含 857 张表单图像、6k 个表单键和值，以及 4k 个表格键和值。我们的数据集还包含三种表单类型：数字、打印和手写，涵盖了多样的表单外观和布局。我们提出了一种基于稳健位置和逻辑关系的表单键值信息提取框架。使用该数据集 Form-NLU，我们首先检验了用于表单布局理解的强大目标检测模型，然后在该数据集上评估了关键信息提取任务，为不同类型的表单和键提供了细粒度的结果。此外，我们使用现成的 pdf 布局提取工具对其进行了检验，证明了其在实际场景中的可行性。
英文摘要：
Compared to general document analysis tasks, form document structure understanding and retrieval are challenging. Form documents are typically made by two types of authors; A form designer, who develops the form structure and keys, and a form user, who fills out form values based on the provided keys. Hence, the form values may not be aligned with the form designer's intention (structure and keys) if a form user gets confused. In this paper, we introduce Form-NLU, the first novel dataset for form structure understanding and its key and value information extraction, interpreting the form designer's intent and the alignment of user-written value on it. It consists of 857 form images, 6k form keys and values, and 4k table keys and values. Our dataset also includes three form types: digital, printed, and handwritten, which cover diverse form appearances and layouts. We propose a robust positional and logical relation-based form key-value information extraction framework. Using this dataset, Form-NLU, we first examine strong object detection models for the form layout understanding, then evaluate the key information extraction task on the dataset, providing fine-grained results for different types of forms and keys. Furthermore, we examine it with the off-the-shelf pdf layout extraction tool and prove its feasibility in real-world cases.
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。
