With margin-based losses that allow positive triples to score below a bound rather than exactly zero, TransE can encode symmetric and reflexive relations, and a new complex-space variant TransComplEx gives competitive results.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Toward Understanding The Effect Of Loss function On Then Performance Of Knowledge Graph Embedding
With margin-based losses that allow positive triples to score below a bound rather than exactly zero, TransE can encode symmetric and reflexive relations, and a new complex-space variant TransComplEx gives competitive results.