报告题目：A Survey of Deep Learning Approaches for OCR andDocument Understanding

论文出处：ArXiv:2020 

作者：Nishant Subramani, Alexandre Matton, Malcolm Greaves, Adrian Lam

单位：Scale AI，Intel Labs

报告人：连敏

报告时间：2022年9月19日 下午 2:30

报告地点：贵州大学北校区博学楼624室

摘要：Documents are a core part of many businesses in many fields such as law, finance,and technology among others. Automatic understanding of documents such asinvoices, contracts, and resumes is lucrative, opening up many new avenues ofbusiness. The fields of natural language processing and computer vision have seentremendous progress through the development of deep learning such that thesemethods have started to become infused in contemporary document understandingsystems. In this survey paper, we review different techniques for document under-standing for documents written in English and consolidate methodologies presentin literature to act as a jumping-off point for researchers exploring this area.