arXiv Analytics

Sign in

arXiv:1603.04513 [cs.CL]AbstractReferencesReviewsResources

Multichannel Variable-Size Convolution for Sentence Classification

Wenpeng Yin, Hinrich Schütze

Published 2016-03-15Version 1

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.

Related articles: Most relevant | Search more
arXiv:1905.08941 [cs.CL] (Published 2019-05-22)
Augmenting Data with Mixup for Sentence Classification: An Empirical Study
arXiv:1810.01656 [cs.CL] (Published 2018-10-03)
A Comparative Study of Neural Network Models for Sentence Classification
arXiv:1912.13106 [cs.CL] (Published 2019-12-30)
An Empirical Study of Factors Affecting Language-Independent Models