A hyperparameter sensitivity study of AGCNN for sentence classification, with tuned settings improving accuracy by roughly 0.45 to 0.81 percentage points on the same six datasets used for tuning.
Se mantic clustering and convolutional neural network for short text ca tegorization
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
-
A Sensitivity Analysis of Attention-Gated Convolutional Neural Networks for Sentence Classification
A hyperparameter sensitivity study of AGCNN for sentence classification, with tuned settings improving accuracy by roughly 0.45 to 0.81 percentage points on the same six datasets used for tuning.