PNRank: Unsupervised ranking of person name entities from noisy OCR text.
Haimonti DuttaAayushee GuptaPublished in: Decis. Support Syst. (2022)
Keyphrases
- text recognition
- optical character recognition
- ocr systems
- printed documents
- document processing
- text extraction
- entity extraction
- text segmentation
- character recognition
- document analysis
- entity search
- cross media retrieval
- document images
- information retrieval
- entity ranking
- text processing
- ranking algorithm
- post processing
- printed text
- named entity disambiguation
- person names
- page layout
- unsupervised learning
- textual features
- scanned documents
- web people search
- text lines
- error correction
- ranking functions
- text mining
- text information
- learning to rank
- preprocessing
- keywords
- handwritten documents
- content features
- text summarization
- scanned images
- text documents
- supervised learning