Existing methods for Visual Information Extraction (VIE) from form-like
documents typically fragment the process into separate subtasks, such as key
information extraction, key-value pair extraction, and choice group extraction.
However, these approaches often overlook the hierarchical structure of form
documents, including hierarchical key-value pairs and hierarchical choice
groups. To address these limitations, we present a new perspective, reframing
VIE as a relation prediction problem and unifying labels of different tasks
into a single label space. This unified approach allows for the definition of
various relation types and effectively tackles hierarchical relationships in
form-like documents. In line with this perspective, we present UniVIE, a
unified model that addresses the VIE problem comprehensively. UniVIE functions
using a coarse-to-fine strategy. It initially generates tree proposals through
a tree proposal network, which are subsequently refined into hierarchical trees
by a relation decoder module. To enhance the relation prediction capabilities
of UniVIE, we incorporate two novel tree constraints into the relation decoder:
a tree attention mask and a tree level embedding. Extensive experimental
evaluations on both our in-house dataset HierForms and a publicly available
dataset SIBR, substantiate that our method achieves state-of-the-art results,
underscoring the effectiveness and potential of our unified approach in
advancing the field of VIE.

现有的视觉信息提取方法通常将从表单样式文档中提取信息的过程分解为不同的子任务，我们提出了一种新的视角，将其重新定义为关系预测问题，并统一了不同任务的标签，以解决表单文档中的层次关系。我们提出的统一模型 UniVIE 通过构建树提案和关系解码模块来全面解决视觉信息提取问题，通过引入树注意力掩码和树级别嵌入来增强关系预测能力。在我们的数据集 HierForms 和公开数据集 SIBR 上进行的广泛实验评估证明了我们方法达到了最先进的结果，突显了我们统一方法在推进视觉信息提取领域的有效性和潜力。