Using visual cues for extraction of tabular data from arbitrary HTML documents.
Bernhard KrüplMarcus HerzogWolfgang GatterbauerPublished in: WWW (Special interest tracks and posters) (2005)
Keyphrases
- visual cues
- tabular data
- html documents
- automatic extraction
- low level
- visual information
- web documents
- web pages
- semantic information
- semi structured
- web content
- structured documents
- differential privacy
- information extraction
- keywords
- key frames
- xml documents
- semistructured data
- feature selection
- digital libraries
- machine learning
- high level
- multimedia
- semi structured data
- metadata