A Library Perspective on Nearly-Unsupervised Information Extraction Workflows in Digital Libraries.
Hermann KrollJan PirklbauerFlorian PlötzkyWolf-Tilo BalkePublished in: CoRR (2022)
Keyphrases
- digital libraries
- information extraction
- text mining
- precision and recall
- digital collections
- natural language processing
- information retrieval
- document image analysis
- named entity recognition
- bibliographic information
- free text
- semi supervised
- data processing
- machine learning
- advanced technology
- university library
- unsupervised learning
- relation extraction
- multimedia
- question answering
- machine translation
- web services
- metadata
- named entities
- conditional random fields
- semi structured
- structured data
- information resources
- data driven
- natural language
- technology advances
- extracting meaningful
- open domain
- workflow systems
- unsupervised manner
- resource discovery
- natural language text
- relational learning
- word sense disambiguation
- web mining
- text documents
- supervised learning
- data extraction
- digital library systems
- business processes
- data mining