A sifted multi-task learning model with gated and attention-based shared feature selection reports state-of-the-art F1 on RumourEval and PHEME for fake news detection.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Different Absorption from the Same Sharing: Sifted Multi-task Learning for Fake News Detection
A sifted multi-task learning model with gated and attention-based shared feature selection reports state-of-the-art F1 on RumourEval and PHEME for fake news detection.