FUSION: Feature-based Processing of Heterogeneous Documents for Automated Information Extraction.
Michael SildatkeHendrik KarwanniBodo KraftAlbert ZündorfPublished in: ICSOFT (2022)
Keyphrases
- information extraction
- web documents
- text documents
- free text
- information retrieval
- text processing
- unstructured documents
- natural language text
- textual data
- text analysis
- document collections
- natural language processing
- unstructured text
- precision and recall
- information retrieval systems
- named entity recognition
- data fusion
- semi automated
- document retrieval
- heterogeneous collections
- keywords
- named entities
- document classification
- question answering
- machine learning
- web mining
- structured data
- real time
- data processing
- document clustering
- textual information
- database
- user queries
- information fusion
- text mining
- image features
- multi sensor
- semi structured
- image fusion
- relation extraction
- data extraction
- information extraction systems
- xml documents