Nougat: Neural Optical Understanding for Academic Documents.
Lukas BlecherGuillem CucurullThomas ScialomRobert StojnicPublished in: CoRR (2023)
Keyphrases
- information retrieval systems
- information retrieval
- network architecture
- document collections
- document retrieval
- xml documents
- web documents
- text documents
- legal documents
- neural network
- metadata
- database
- relevant documents
- document clustering
- bio inspired
- digital documents
- query terms
- document analysis
- retrieved documents
- vector space model
- document classification
- retrieval systems
- keywords
- document representation
- multimedia documents
- document content
- query expansion
- google scholar