A deep network with visual text composition behavior

DOIResolve DOI: http://doi.org/10.18653/v1/P17-2059
AuthorSearch for:
TypeArticle
Proceedings titleProceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Volume 2: Short Papers
ConferenceThe 55th Annual Meeting of the Association for Computational Linguistics, 30 July - August 4, 2017, Vancouver, BC., Canada
Pages372377
AbstractWhile natural languages are composi- tional, how state-of-the-art neural models achieve compositionality is still unclear. We propose a deep network, which not only achieves competitive accuracy for text classification, but also exhibits compositional behavior. That is, while creating hierarchical representations of a piece of text, such as a sentence, the lower layers of the network distribute their layer-specific attention weights to individual words. In contrast, the higher layers compose meaningful phrases and clauses, whose lengths increase as the networks get deeper until fully composing the sentence.
Publication date
PublisherAssociation for Computational Linguistics
LanguageEnglish
AffiliationInformation and Communication Technologies; National Research Council Canada
Peer reviewedYes
NPARC number23002276
Export citationExport as RIS
Report a correctionReport a correction
Record identifiera6bdaa46-5f05-4281-8ccc-bf160e7a5aff
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: