Robust named entity detection from optical character recognition output.
Krishna SubramanianRohit PrasadPrem NatarajanPublished in: Int. J. Document Anal. Recognit. (2011)
Keyphrases
- named entities
- optical character recognition
- text recognition
- named entity extraction
- information extraction
- page segmentation
- named entity recognition
- character recognition
- question answering
- document images
- text mining
- natural language processing
- relation extraction
- ocr systems
- co occurrence
- annotated corpus
- object detection
- databases
- pattern recognition
- partial occlusion
- text lines
- noun phrases
- unsupervised learning
- knowledge representation