TY - GEN
T1 - Multichannel variable-size convolution for sentence classification
AU - Yin, Wenpeng
AU - Schütze, Hinrich
N1 - Publisher Copyright:
© 2015 Association for Computational Linguistics.
PY - 2015
Y1 - 2015
N2 - 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 large-scale Twitter sentiment prediction and on subjectivity classification.
AB - 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 large-scale Twitter sentiment prediction and on subjectivity classification.
UR - http://www.scopus.com/inward/record.url?scp=85072774032&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85072774032&partnerID=8YFLogxK
U2 - 10.18653/v1/k15-1021
DO - 10.18653/v1/k15-1021
M3 - Conference contribution
AN - SCOPUS:85072774032
T3 - CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings
SP - 204
EP - 214
BT - CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings
PB - Association for Computational Linguistics (ACL)
T2 - 19th Conference on Computational Natural Language Learning, CoNLL 2015
Y2 - 30 July 2015 through 31 July 2015
ER -