Multichannel variable-size convolution for sentence classification

Wenpeng Yin, Hinrich Schütze

Research output: Chapter in Book/Report/Conference proceedingConference contribution

86 Scopus citations

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 large-scale Twitter sentiment prediction and on subjectivity classification.

Original languageEnglish (US)
Title of host publicationCoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages204-214
Number of pages11
ISBN (Electronic)9781941643778
DOIs
StatePublished - 2015
Event19th Conference on Computational Natural Language Learning, CoNLL 2015 - Beijing, China
Duration: Jul 30 2015Jul 31 2015

Publication series

NameCoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings

Conference

Conference19th Conference on Computational Natural Language Learning, CoNLL 2015
Country/TerritoryChina
CityBeijing
Period7/30/157/31/15

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Human-Computer Interaction
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Multichannel variable-size convolution for sentence classification'. Together they form a unique fingerprint.

Cite this