easIE: Easy-to-Use Information Extraction for Constructing CSR Databases From the Web.
Vasiliki GkatziakiSymeon PapadopoulosRichard A. MillsSotiris DiplarisIoannis TsampoulatidisIoannis KompatsiarisPublished in: ACM Trans. Internet Techn. (2018)
Keyphrases
- information extraction
- databases
- web mining
- web documents
- data extraction
- website
- database
- ontology population
- web information extraction
- textual data
- web content
- web data
- web applications
- text mining
- web sources
- natural language processing
- named entities
- web resources
- deep web
- query interface
- web databases
- relational databases
- web users
- linked data
- heterogeneous information sources
- precision and recall
- information retrieval
- information sources
- database applications
- data integration
- web technologies
- knowledge discovery
- web pages
- free text
- text documents
- named entity recognition
- structured data
- link analysis
- semi structured
- end users
- conditional random fields
- data management
- domain specific
- metadata
- co occurrence
- multimedia information
- web search
- query processing