DSLFM-KGC couples sparse latent community models with BERT text features and contrastive learning, improving state-of-the-art scores on Wikidata5M-Ind, WN18RR, and UMLS.
Mixed membership stochastic blockmodels
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Sparse Latent Feature Models for Knowledge Graph Completion
DSLFM-KGC couples sparse latent community models with BERT text features and contrastive learning, improving state-of-the-art scores on Wikidata5M-Ind, WN18RR, and UMLS.