HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures

TL;DR

This paper introduces HRDoc, a large-scale dataset and a novel hierarchical document structure parsing system to reconstruct semantic structures from multi-page documents, advancing NLP and CV applications.

Contribution

The paper presents HRDoc, a new dataset for multi-page document structure reconstruction, and proposes a hierarchical parsing system that outperforms baseline methods.

Findings

The DSPS model significantly outperforms baseline methods.

HRDoc dataset contains nearly 2 million semantic units.

The approach effectively reconstructs multi-page document structures.

Abstract

The problem of document structure reconstruction refers to converting digital or scanned documents into corresponding semantic structures. Most existing works mainly focus on splitting the boundary of each element in a single document page, neglecting the reconstruction of semantic structure in multi-page documents. This paper introduces hierarchical reconstruction of document structures as a novel task suitable for NLP and CV fields. To better evaluate the system performance on the new task, we built a large-scale dataset named HRDoc, which consists of 2,500 multi-page documents with nearly 2 million semantic units. Every document in HRDoc has line-level annotations including categories and relations obtained from rule-based extractors and human annotators. Moreover, we proposed an encoder-decoder-based hierarchical document structure parsing system (DSPS) to tackle this problem. By adopting a multi-modal bidirectional encoder and a structure-aware GRU decoder with soft-mask operation, the DSPS model surpass the baseline method by a large margin. All scripts and datasets will be made publicly available at https://github.com/jfma-USTC/HRDoc.