A hard-parameter-sharing multi-task neural network that jointly predicts check-worthiness labels from nine fact-checking sources outperforms single-task models on the CW-USPD-2016 dataset.
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
-
It Takes Nine to Smell a Rat: Neural Multi-Task Learning for Check-Worthiness Prediction
A hard-parameter-sharing multi-task neural network that jointly predicts check-worthiness labels from nine fact-checking sources outperforms single-task models on the CW-USPD-2016 dataset.