Across nine NLP datasets, multi-task learning with linguistic-hierarchy supervision gives the largest average gain among five MTL mechanisms, and the best hybrid combines hierarchies, gating, and label embedding, not all five.
Rich, Multitask learning, Machine Learning.
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Empirical Evaluation of Multi-task Learning in Deep Neural Networks for Natural Language Processing
Across nine NLP datasets, multi-task learning with linguistic-hierarchy supervision gives the largest average gain among five MTL mechanisms, and the best hybrid combines hierarchies, gating, and label embedding, not all five.