Abstract | ||
---|---|---|
Type information is very valuable in knowledge bases. However, most large open knowledge bases are incomplete with respect to type information, and, at the same time, contain noisy and incorrect data. That makes classic type inference by reasoning difficult. In this paper, we propose the heuristic link-based type inference mechanism SDType, which can handle noisy and incorrect data. Instead of leveraging T-box information from the schema, SDType takes the actual use of a schema into account and thus is also robust to misused schema elements. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1007/978-3-642-41335-3_32 | International Semantic Web Conference (1) |
Keywords | Field | DocType |
link-based classification,noisy data,type inference | Data mining,Noisy data,Heuristic,Computer science,Type inference,Open knowledge,Artificial intelligence,Schema (psychology),RDF,Machine learning | Conference |
Volume | ISSN | Citations |
8218 | 0302-9743 | 60 |
PageRank | References | Authors |
2.05 | 16 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Heiko Paulheim | 1 | 1095 | 84.19 |
Christian Bizer | 2 | 8448 | 524.93 |