Self-Balanced Dropout replaces zeroed units with a trainable mask to reduce co-adaptation, but the theoretical justification is invalid and empirical gains are modest.
Multichannel Variable-Size Convolution for Sentence Classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We propose MVCNN, a convolution neural network (CNN) architecture for sentence classification. It (i) combines diverse versions of pretrained word embeddings and (ii) extracts features of multigranular phrases with variable-size convolution filters. We also show that pretraining MVCNN is critical for good performance. MVCNN achieves state-of-the-art performance on four tasks: on small-scale binary, small-scale multi-class and largescale Twitter sentiment prediction and on subjectivity classification.
fields
cs.CL 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Self-Balanced Dropout
Self-Balanced Dropout replaces zeroed units with a trainable mask to reduce co-adaptation, but the theoretical justification is invalid and empirical gains are modest.