Multichannel Variable-Size Convolution for Sentence Classification
Computation and Language
2016-03-16 v1
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.
Cite
@article{arxiv.1603.04513,
title = {Multichannel Variable-Size Convolution for Sentence Classification},
author = {Wenpeng Yin and Hinrich Schütze},
journal= {arXiv preprint arXiv:1603.04513},
year = {2016}
}
Comments
in Proceeding of CoNLL2015