|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Knowledge graphs are important resources for many artificial intelligence tasks but often suffer from incompleteness.
#20 best model for Link Prediction on WN18RR
Most conventional knowledge embedding methods encode both entities (concepts and instances) and relations as vectors in a low dimensional semantic space equally, ignoring the difference between concepts and instances.
SOTA for Link Prediction on YAGO39K
Experimental results demonstrate that our confidence-aware models achieve significant and consistent improvements on all tasks, which confirms the capability of CKRL modeling confidence with structural information in both KG noise detection and knowledge representation learning.
The main idea is to frame the task of triple classification as a debate game between two reinforcement learning agents which extract arguments -- paths in the knowledge graph -- with the goal to promote the fact being true (thesis) or the fact being false (antithesis), respectively.
Commonsense knowledge graphs (CKGs) like Atomic and ASER are substantially different from conventional KGs as they consist of much larger number of nodes formed by loosely-structured text, which, though, enables them to handle highly diverse queries in natural language related to commonsense, leads to unique challenges for automatic KG construction methods.