FCKT improves targeted sentiment analysis through fine-grained transfer of aspect boundary knowledge into sentiment prediction, using token-level contrastive learning and an alternating real/predicted training strategy.
A span-based model for aspect terms extraction and aspect sentiment classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FCKT: Fine-Grained Cross-Task Knowledge Transfer with Semantic Contrastive Learning for Targeted Sentiment Analysis
FCKT improves targeted sentiment analysis through fine-grained transfer of aspect boundary knowledge into sentiment prediction, using token-level contrastive learning and an alternating real/predicted training strategy.