A hybrid network combining per-word convolution, two LSTM paths, and attention matches or beats recurrent-convolutional baselines on seven text tasks with fewer parameters.
The Journal of Machine Learning Research, 15(1):1929–1958
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
-
Sequential Learning of Convolutional Features for Effective Text Classification
A hybrid network combining per-word convolution, two LSTM paths, and attention matches or beats recurrent-convolutional baselines on seven text tasks with fewer parameters.