DeepPSL: End-to-end perception and reasoning

no code implementations • 28 Sep 2021 • Sridhar Dasaratha, Sai Akhil Puranam, Karmvir Singh Phogat, Sunil Reddy Tiyyagura, Nigel P. Duffy

We believe that this approach represents an interesting direction for the integration of deep learning and reasoning techniques with applications to knowledge base learning, multi-task learning, and explainability.

Image Classification Multi-Task Learning +1

DeepCPCFG: Deep Learning and Context Free Grammars for End-to-End Information Extraction

1 code implementation • 10 Mar 2021 • Freddy C. Chua, Nigel P. Duffy

We address the challenge of extracting structured information from business documents without detailed annotations.

Document Enhancement System Using Auto-encoders

no code implementations • NeurIPS Workshop Document_Intelligen 2019 • Mehrdad J. Gangeh, Sunil R. Tiyyagura, Sridhar V. Dasaratha, Hamid Motahari, Nigel P. Duffy

The conversion of scanned documents to digital forms is performed using an Optical Character Recognition (OCR) software.

Denoising Document Enhancement +2