PEneo：统一行提取、行分组和实体链接以实现端到端文档对提取
PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction
AI总结：
本文提出统一框架PEneo，通过行提取、行分组和实体链接三个并发子任务实现端到端文档对提取，缓解错误传播并处理多行实体，在多个基准上结合不同骨干网络大幅提升F1性能。
摘要：
文档对提取旨在从视觉富文档中识别键和值实体及其关系。现有大多数方法将其分为两个独立任务：语义实体识别（SER）和关系提取（RE）。然而，简单地将SER和RE串行连接会导致严重的错误传播，且无法处理现实场景中的多行实体等情况。为了解决这些问题，本文提出了一种新框架PEneo（Pair Extraction new decoder option），在统一流水线中执行文档对提取，包含三个并发子任务：行提取、行分组和实体链接。该方法缓解了错误累积问题并能处理多行实体情况。此外，为更好评估模型性能并促进未来研究，我们引入RFUND——常用FUNSD和XFUND数据集的重新标注版本，使其更准确并覆盖现实情况。在多个基准上的实验表明，PEneo优于先前流水线，结合LiLT和LayoutLMv3等骨干网络大幅提升性能（如RFUND-EN上F1提升19.89%-22.91%），验证其有效性与通用性。代码及新标注见 https://github.com/ZeningLin/PEneo。
英文摘要：
Document pair extraction aims to identify key and value entities as well as their relationships from visually-rich documents. Most existing methods divide it into two separate tasks: semantic entity recognition (SER) and relation extraction (RE). However, simply concatenating SER and RE serially can lead to severe error propagation, and it fails to handle cases like multi-line entities in real scenarios. To address these issues, this paper introduces a novel framework, PEneo (Pair Extraction new decoder option), which performs document pair extraction in a unified pipeline, incorporating three concurrent sub-tasks: line extraction, line grouping, and entity linking. This approach alleviates the error accumulation problem and can handle the case of multi-line entities. Furthermore, to better evaluate the model's performance and to facilitate future research on pair extraction, we introduce RFUND, a re-annotated version of the commonly used FUNSD and XFUND datasets, to make them more accurate and cover realistic situations. Experiments on various benchmarks demonstrate PEneo's superiority over previous pipelines, boosting the performance by a large margin (e.g., 19.89%-22.91% F1 score on RFUND-EN) when combined with various backbones like LiLT and LayoutLMv3, showing its effectiveness and generality. Codes and the new annotations are available at https://github.com/ZeningLin/PEneo.
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。
