Visual NLP – Combining Computer Vision and Text Mining for Intelligent Document Processing

Many businesses depend on paper documents or documents stored as images, such as receipts, manifests, invoices, medical reports, contracts, waivers, leases, forms, and audit records digitized with scanners. Up until now, extracting data from these images mainly involved extracting the text through OCR and using NLP techniques, while neglecting the layout and style information which are often vital for document image understanding. Novel deep learning techniques combine features from computer vision and NLP into unified models, resulting in improved state-of-the-art accuracy for form understanding and visual information extraction. This talk shares real applications of these models to digitize and analyze documents with the purpose of extracting meaningful and easily exploitable data.