A Survey of Deep Learning Approaches for OCR and Document Understanding
arXiv:2011.13534
Abstract
Documents are a core part of many businesses in many fields such as law, finance, and technology among others. Automatic understanding of documents such as invoices, contracts, and resumes is lucrative, opening up many new avenues of business. The fields of natural language processing and computer vision have seen tremendous progress through the development of deep learning such that these methods have started to become infused in contemporary document understanding systems. In this survey paper, we review different techniques for document understanding for documents written in English and consolidate methodologies present in literature to act as a jumping-off point for researchers exploring this area.
arXiv commentAccepted to the ML-RSA Workshop at NeurIPS2020. 15 pages (10 + References)
References in corpus (24)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Sequence to Sequence Learning with Neural Networks
- YOLOv3: An Incremental Improvement
- Longformer: The Long-Document Transformer
- Unsupervised Data Augmentation for Consistency Training
- TextBoxes++: A Single-Shot Oriented Scene Text Detector
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
- Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
- Generating Long Sequences with Sparse Transformers
- TextBoxes: A Fast Text Detector with a Single Deep Neural Network
- ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction
- Reformer: The Efficient Transformer
- Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
- Detecting Curve Text in the Wild: New Dataset and New Solution
- Scene Text Detection via Holistic, Multi-Channel Prediction
- Rethinking Attention with Performers
- BERTgrid: Contextualized Embedding for 2D Document Representation and Understanding
- CUTIE: Learning to Understand Documents with Convolutional Universal Text Information Extractor
- DocBank: A Benchmark Dataset for Document Layout Analysis
- Spatial Dependency Parsing for Semi-Structured Document Information Extraction
- Towards a Multi-modal, Multi-task Learning based Pre-training Framework for Document Representation Learning
- CDeC-Net: Composite Deformable Cascade Network for Table Detection in Document Images
- Discovering Useful Sentence Representations from Large Pretrained Language Models
- PAG2ADMG: An Algorithm for the Complete Causal Enumeration of a Markov Equivalence Class