Training a multi-task model on predicted auxiliary labels for test sentences improves dependency and semantic tagging accuracy over plain multi-task learning, with the largest gains in low-resource settings.
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
-
Transductive Auxiliary Task Self-Training for Neural Multi-Task Models
Training a multi-task model on predicted auxiliary labels for test sentences improves dependency and semantic tagging accuracy over plain multi-task learning, with the largest gains in low-resource settings.