End-to-end hard word clustering via Gumbel-Softmax produces smaller, parameter-efficient text classifiers.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Smaller Text Classifiers with Discriminative Cluster Embeddings
End-to-end hard word clustering via Gumbel-Softmax produces smaller, parameter-efficient text classifiers.