English

Visually Guided Generative Text-Layout Pre-training for Document Intelligence

Computation and Language 2024-03-28 v2 Computer Vision and Pattern Recognition

Abstract

Prior study shows that pre-training techniques can boost the performance of visual document understanding (VDU), which typically requires models to gain abilities to perceive and reason both document texts and layouts (e.g., locations of texts and table-cells). To this end, we propose visually guided generative text-layout pre-training, named ViTLP. Given a document image, the model optimizes hierarchical language and layout modeling objectives to generate the interleaved text and layout sequence. In addition, to address the limitation of processing long documents by Transformers, we introduce a straightforward yet effective multi-segment generative pre-training scheme, facilitating ViTLP to process word-intensive documents of any length. ViTLP can function as a native OCR model to localize and recognize texts of document images. Besides, ViTLP can be effectively applied to various downstream VDU tasks. Extensive experiments show that ViTLP achieves competitive performance over existing baselines on benchmark VDU tasks, including information extraction, document classification, and document question answering.

Keywords

Cite

@article{arxiv.2403.16516,
  title  = {Visually Guided Generative Text-Layout Pre-training for Document Intelligence},
  author = {Zhiming Mao and Haoli Bai and Lu Hou and Jiansheng Wei and Xin Jiang and Qun Liu and Kam-Fai Wong},
  journal= {arXiv preprint arXiv:2403.16516},
  year   = {2024}
}

Comments

Accepted to NAACL 2024 main conference. The first version of this paper was submitted to OpenReview (https://openreview.net/forum?id=ARtBIBAmNR) in June 2023

R2 v1 2026-06-28T15:32:19.826Z