Data Centric Domain Adaptation for Historical Text with OCR Errors.
Luisa MärzStefan SchweterNina PörnerBenjamin RothHinrich SchützePublished in: ICDAR (2) (2021)
Keyphrases
- domain adaptation
- data centric
- multiple sources
- business processes
- information management
- cross domain
- data driven
- data management
- distributed systems
- application development
- semi supervised
- sentiment classification
- labeled data
- database
- transfer learning
- routing protocol
- data representation
- text mining
- keywords
- optical character recognition
- semi supervised learning
- document classification
- wireless sensor networks
- information retrieval
- text documents
- data storage
- target domain
- text classification
- co occurrence
- information integration
- data mining