Document AI: Benchmarks, Models and Applications

TL;DR

This paper reviews recent advances in Document AI, covering models, tasks, datasets, and future research directions, emphasizing deep learning techniques and their applications in understanding business documents.

Contribution

It provides a comprehensive overview of current models, benchmarks, and methods in Document AI, highlighting the evolution from heuristic rules to deep learning approaches.

Findings

Deep learning has significantly advanced Document AI capabilities.

Benchmark datasets are crucial for evaluating Document AI models.

Future research directions include integrating multi-modal data and improving model interpretability.

Abstract

Document AI, or Document Intelligence, is a relatively new research topic that refers to the techniques for automatically reading, understanding, and analyzing business documents. It is an important research direction for natural language processing and computer vision. In recent years, the popularity of deep learning technology has greatly advanced the development of Document AI, such as document layout analysis, visual information extraction, document visual question answering, document image classification, etc. This paper briefly reviews some of the representative models, tasks, and benchmark datasets. Furthermore, we also introduce early-stage heuristic rule-based document analysis, statistical machine learning algorithms, and deep learning approaches especially pre-training methods. Finally, we look into future directions for Document AI research.