Discourse Sense Flows: Modelling the Rhetorical Style of Documents across Various Domains.
René KnaebelManfred StedePublished in: EMNLP (Findings) (2023)
Keyphrases
- information retrieval systems
- document collections
- rhetorical structure theory
- web documents
- information retrieval
- relevant documents
- metadata
- xml documents
- text documents
- document analysis
- real world
- authorship attribution
- legal documents
- retrieved documents
- document representation
- document classification
- database
- text classification
- keywords
- natural language
- digital documents
- plagiarism detection
- application domains
- structured documents
- vector space model
- document set
- semantic relationships
- relational databases
- test collection
- document content
- user queries
- free text
- word spotting
- document clustering