Multimedia information extraction from HTML product catalogues.
Martin LabskýPavel PraksVojtech SvátekOndrej SvábPublished in: DATESO (2005)
Keyphrases
- information extraction
- multimedia
- semi structured
- structured data
- natural language processing
- machine learning
- text mining
- multimedia data
- named entity recognition
- relation extraction
- precision and recall
- free text
- web documents
- life cycle
- conditional random fields
- text documents
- multimedia content
- textual data
- information retrieval
- text processing
- data extraction
- multimedia information retrieval
- digital media
- question answering
- digital libraries
- relational learning
- multimedia documents
- multimedia information
- open domain
- cultural heritage
- web mining
- machine translation
- metadata
- text summarization
- web browser
- named entities
- learning environment
- e learning
- data mining
- product quality
- databases