A two-stage recipe that initializes MAML with BERT reaches 90.01% accuracy on few-shot ARSC sentiment classification, a new state of the art.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When Low Resource NLP Meets Unsupervised Language Model: Meta-pretraining Then Meta-learning for Few-shot Text Classification
A two-stage recipe that initializes MAML with BERT reaches 90.01% accuracy on few-shot ARSC sentiment classification, a new state of the art.