A library perspective on nearly-unsupervised information extraction workflows in digital libraries.
Hermann KrollJan PirklbauerFlorian PlötzkyWolf-Tilo BalkePublished in: JCDL (2022)
Keyphrases
- digital libraries
- information extraction
- digital collections
- bibliographic information
- university library
- precision and recall
- metadata
- advanced technology
- viewpoint
- supervised learning
- document image analysis
- structured data
- question answering
- free text
- text mining
- natural language processing
- machine learning
- cultural heritage
- unsupervised learning
- web documents
- named entities
- data processing
- data driven
- digital content
- technology advances
- digital resources
- ontology based information extraction
- unsupervised manner
- digital library collections
- textual data
- named entity recognition
- word sense disambiguation
- semi structured
- web mining
- semi supervised
- web services
- relation extraction
- resource discovery
- business process
- business processes
- natural language
- extracting meaningful
- database