Intellix - End-User Trained Information Extraction for Document Archiving.
Daniel SchusterKlemens MuthmannDaniel EsserAlexander SchillMichael BergerChristoph WeidlingKamil AliyevAndreas HofmeierPublished in: ICDAR (2013)
Keyphrases
- cultural heritage
- end users
- information extraction
- text documents
- web documents
- information retrieval
- unstructured documents
- multimedia
- application development
- text summarization
- user requirements
- text mining
- user interface
- natural language processing
- document classification
- retrieval systems
- free text
- precision and recall
- web applications
- business intelligence
- information retrieval systems
- document images
- user friendliness
- user experience
- named entity recognition
- user driven
- named entities
- database
- question answering
- service providers
- semi structured
- search tools
- keywords
- machine learning
- machine translation
- data integration
- document collections
- training set