BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning.

Asa Cooper Stickland Iain Murray

Published in: ICML (2019)

Keyphrases

multi task learning
multi task
learning tasks
gaussian processes
multiple tasks
learning problems
machine learning
pedagogical agents
theoretical analysis
multi class
multitask learning
feature selection
model selection
high order