CLNov 16, 2021

Document AI: Benchmarks, Models and Applications

arXiv:2111.08609v197 citations
Originality Synthesis-oriented
AI Analysis

It provides a survey of Document AI, which is important for natural language processing and computer vision, but is incremental as it summarizes existing work.

This paper reviews the field of Document AI, covering benchmarks, models, and applications for automatically reading and analyzing business documents, but does not present new results or concrete numbers.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes