TocBERT: Medical Document Structure Extraction Using Bidirectional Transformers.
Majd SalehSarra BaghdadiStéphane PaqueletPublished in: CoRR (2024)
Keyphrases
- structure extraction
- document structure
- document layout
- inex book track
- structured documents
- document retrieval
- document images
- information retrieval systems
- xml documents
- web documents
- query terms
- document representation
- document collections
- user queries
- retrieval systems
- document clustering
- text summarization
- text documents
- feature selection
- vector space model
- probabilistic model
- digital libraries