UnSupDLA: Towards Unsupervised Document Layout Analysis.
Talha Uddin SheikhTahira ShehzadiKhurram Azeem HashmiDidier StrickerMuhammad Zeshan AfzalPublished in: CoRR (2024)
Keyphrases
- unsupervised learning
- information retrieval
- topic discovery
- document classification
- information retrieval systems
- data driven
- document collections
- document clustering
- semi supervised
- completely unsupervised
- retrieval systems
- structured documents
- tf idf
- document content
- document processing
- unsupervised manner
- data sets
- document images
- web documents
- document retrieval
- text documents
- document analysis
- supervised learning
- cf loadingtexthtml
- keywords
- database