Detect-Order-Construct: A Tree Construction based Approach for Hierarchical Document Structure Analysis

TL;DR

This paper introduces a tree construction approach for hierarchical document structure analysis, integrating detection, reading order prediction, and structure building, achieving state-of-the-art results on multiple datasets.

Contribution

It proposes a comprehensive end-to-end framework for hierarchical document analysis and introduces the Comp-HRDoc benchmark for evaluating such systems.

Findings

Achieved state-of-the-art performance on PubLayNet and DocLayNet datasets.

Developed a new benchmark, Comp-HRDoc, for hierarchical document structure evaluation.

Demonstrated effective simultaneous handling of multiple document analysis subtasks.

Abstract

Document structure analysis (aka document layout analysis) is crucial for understanding the physical layout and logical structure of documents, with applications in information retrieval, document summarization, knowledge extraction, etc. In this paper, we concentrate on Hierarchical Document Structure Analysis (HDSA) to explore hierarchical relationships within structured documents created using authoring software employing hierarchical schemas, such as LaTeX, Microsoft Word, and HTML. To comprehensively analyze hierarchical document structures, we propose a tree construction based approach that addresses multiple subtasks concurrently, including page object detection (Detect), reading order prediction of identified objects (Order), and the construction of intended hierarchical structure (Construct). We present an effective end-to-end solution based on this framework to demonstrate its performance. To assess our approach, we develop a comprehensive benchmark called Comp-HRDoc, which evaluates the above subtasks simultaneously. Our end-to-end system achieves state-of-the-art performance on two large-scale document layout analysis datasets (PubLayNet and DocLayNet), a high-quality hierarchical document structure reconstruction dataset (HRDoc), and our Comp-HRDoc benchmark. The Comp-HRDoc benchmark will be released to facilitate further research in this field.