PolyBERT combines a poly-encoder cross-attention fusion of token and sequence semantics with batch contrastive learning, achieving 81.0 all-words F1 and 37.6% training time savings.
Moving down the long tail of word sense disambiguation with gloss informed bi-encoders,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
PolyBERT: Fine-Tuned Poly Encoder BERT-Based Model for Word Sense Disambiguation
PolyBERT combines a poly-encoder cross-attention fusion of token and sequence semantics with batch contrastive learning, achieving 81.0 all-words F1 and 37.6% training time savings.