STRAS: A Semantic Textual-Cues Leveraged Rule-Based Approach for Article Separation in Historical Newspapers.
Nancy GirdharMickaël CoustatyAntoine DoucetPublished in: ICADL (1) (2023)
Keyphrases
- natural language
- semantic knowledge
- domain specific
- semantic web
- low level features
- web pages
- semantic content
- domain ontology
- search engine
- natural language understanding
- mid level
- semantic concepts
- semantic network
- semantic similarity
- news articles
- high level
- historical data
- semantic analysis
- semantic information
- user generated
- semantic search
- keywords
- metadata
- semantic representation
- machine learning
- semantic level
- textual features
- semantically equivalent