New method for KG completion from tables that uses graphical models on entity similarities plus embeddings to prioritize novel facts over redundant ones, with tunable precision/recall and higher reported recall.
Proceedings of the IEEE 104(1), 11–33 (2016)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Extracting Novel Facts from Tables for Knowledge Graph Completion (Extended version)
New method for KG completion from tables that uses graphical models on entity similarities plus embeddings to prioritize novel facts over redundant ones, with tunable precision/recall and higher reported recall.