PPN: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts

TL;DR

This paper introduces PPN, a parallel pointer-based network, and a large-scale dataset CLEX for improved key information extraction from complex, visually rich documents, addressing dataset limitations and error propagation issues.

Contribution

The paper presents a new large-scale dataset CLEX and a novel end-to-end PPN model capable of zero-shot and few-shot extraction, enhancing efficiency and accuracy.

Findings

PPN outperforms existing methods on CLEX.

PPN achieves faster inference speed.

CLEX dataset contains 5,860 images with 1,162 categories.

Abstract

Key Information Extraction (KIE) is a challenging multimodal task that aims to extract structured value semantic entities from visually rich documents. Although significant progress has been made, there are still two major challenges that need to be addressed. Firstly, the layout of existing datasets is relatively fixed and limited in the number of semantic entity categories, creating a significant gap between these datasets and the complex real-world scenarios. Secondly, existing methods follow a two-stage pipeline strategy, which may lead to the error propagation problem. Additionally, they are difficult to apply in situations where unseen semantic entity categories emerge. To address the first challenge, we propose a new large-scale human-annotated dataset named Complex Layout form for key information EXtraction (CLEX), which consists of 5,860 images with 1,162 semantic entity categories. To solve the second challenge, we introduce Parallel Pointer-based Network (PPN), an end-to-end model that can be applied in zero-shot and few-shot scenarios. PPN leverages the implicit clues between semantic entities to assist extracting, and its parallel extraction mechanism allows it to extract multiple results simultaneously and efficiently. Experiments on the CLEX dataset demonstrate that PPN outperforms existing state-of-the-art methods while also offering a much faster inference speed.