Lights, Camera, Action! A Framework to Improve NLP Accuracy over OCR documents.
Amit GupteAlexey RomanovSahitya MantravadiDalitso BandaJianjie LiuRaza KhanLakshmanan Ramu MeenalBenjamin HanSoundar SrinivasanPublished in: CoRR (2021)
Keyphrases
- high accuracy
- natural language processing
- information retrieval
- document retrieval
- information retrieval systems
- xml documents
- probabilistic model
- natural language
- post processing
- document analysis
- document images
- free text
- text analysis
- document processing
- scanned documents
- optical character recognition
- hand held
- error correction
- field of view
- document collections
- digital libraries
- computer vision