There are many entity-attribute tables on the Web that can be utilized for enriching the entities of knowledge bases (KBs). This requires the schema mapping (matching) between the Web tables and the huge KBs. Existing solutions on schema mapping are inadequate for mapping a Web table and a KB, because of many reasons such as (1) there are many duplicates of entities and their types in a KB; (2) the schema of KB is often implicit, informal, and evolving over time; (3) the KB is typically very large in volume. In this paper, we propose a pure instance-based schema mapping solution to statistically find the effective mapping between a Web table and a KB via the matched data examples. Besides, we propose efficient solutions on finding the matched data examples as well as the overall mapping of a table and a KB. Experiments over real data sets show that our solution is much more accurate than the two baselines of existing solutions. Results also show that our solution is feasible for the mapping of Web tables to large scale KBs.
展开▼
