A deep ranking cost-sensitive multi-label model is introduced for distant supervision relation extraction that models class ties between relations via ranking losses and rescales costs for imbalance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Deep Ranking Based Cost-sensitive Multi-label Learning for Distant Supervision Relation Extraction
A deep ranking cost-sensitive multi-label model is introduced for distant supervision relation extraction that models class ties between relations via ranking losses and rescales costs for imbalance.