End-to-end multi-view networks for text classification

Download
  1. (PDF, 722 KB)
AuthorSearch for: ; Search for: ; Search for:
TypeArticle
Proceedings titleComputer Science
Article numberarXiv:1704.05907
Pages# of pages: 6
Subjectcomputation and language; learning; neural and evolutionary computing
AbstractWe propose a multi-view network for text classification. Our method automatically creates various views of its input text, each taking the form of soft attention weights that distribute the classifier's focus among a set of base features. For a bag-of-words representation, each view focuses on a different subset of the text's words. Aggregating many such views results in a more discriminative and robust representation. Through a novel architecture that both stacks and concatenates views, we produce a network that emphasizes both depth and width, allowing training to converge quickly. Using our multi-view architecture, we establish new state-of-the-art accuracies on two benchmark tasks.
Publication date
PublisherCornell University Library
Linkhttps://arxiv.org/abs/1704.05907
LanguageEnglish
AffiliationInformation and Communication Technologies; National Research Council Canada
Peer reviewedNo
NPARC number23002277
Export citationExport as RIS
Report a correctionReport a correction
Record identifier0c6ea103-6166-460f-90ac-06eff86608d0
Record created2017-09-28
Record modified2017-09-28
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)
Date modified: