PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction.
Zening LinJiapeng WangTeng LiWenhui LiaoDayi HuangLongfei XiongLianwen JinPublished in: CoRR (2024)
Keyphrases
- line extraction
- end to end
- entity linking
- document images
- knowledge base
- topic modeling
- hough transform
- morphological operations
- semantic search
- topic models
- document analysis
- relevance model
- handwritten documents
- optical character recognition
- web documents
- personalized recommendation
- text lines
- mathematical morphology
- image data
- latent dirichlet allocation
- information retrieval systems
- co occurrence
- multimedia