Knowledge Curation and Knowledge Fusion: Challenges, Models, and Applications
Large-scale knowledge repositories are becoming increasingly important as a foundation for enabling a wide variety of complex applications. In turn, building high-quality knowledge repositories critically depends on the technologies of knowledge curation and knowledge fusion, which share many similar goals with data integration, while facing even more challenges in extracting knowledge from both structured and unstructured data, across a large variety of domains, and in multiple languages.
Our tutorial highlights the similarities and differences between knowledge management and data integration, and has two goals. First, we introduce the Database community to the techniques proposed for the problems of entity linkage and relation extraction by the Knowledge Management, Natural Language Processing, and Machine Learning communities. Second, we give a detailed survey of the work done by these communities in knowledge fusion, which is critical to discover and clean errors present in sources and the many mistakes made in the process of knowledge extraction from sources. Our tutorial is example driven and hopes to build bridges between the Database community and other disciplines to advance research in this important area.
- Xin Luna Dong and Divesh Srivastava, Knowledge Curation and Knowledge Fusion: Challenges, Models, and Applications, SIGMOD 2015, 2015.