Harvesting facts from textual web sources by constrained label propagation.
Yafang WangBin YangLizhen QuMarc SpaniolGerhard WeikumPublished in: CIKM (2011)
Keyphrases
- label propagation
- web sources
- semi supervised learning
- semi supervised
- information sources
- data extraction
- information integration
- semi structured
- web data
- community detection
- multiple sources
- web pages
- website
- deep web
- labeled data
- unlabeled data
- information extraction
- web users
- class labels
- search engine
- data sources
- natural language
- metadata
- pairwise constraints
- multimedia
- spectral clustering
- multi label classification
- information retrieval
- unsupervised learning
- natural language processing
- digital libraries
- query interface
- keywords
- training data
- label information