Document AI: Benchmarks, Models and Applications
arXiv:2111.08609
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.
References in corpus (16)
- Deep Residual Learning for Image Recognition
- TAPAS: Weakly Supervised Table Parsing via Pre-training
- ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction
- Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification
- Fully Convolutional Neural Networks for Page Segmentation of Historical Document Images
- BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding
- LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding
- TNCR: Table Net Detection and Classification Dataset
- Image-based table recognition: data, model, and evaluation
- Modular Multimodal Architecture for Document Classification
- Spatial Dependency Parsing for Semi-Structured Document Information Extraction
- StructuralLM: Structural Pre-training for Form Understanding
- Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution
- LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding
- LAMBERT: Layout-Aware (Language) Modeling for information extraction
- ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents