Login / Signup

Attentive Mimicking: Better Word Embeddings by Attending to Informative Contexts.

Timo SchickHinrich Schütze
Published in: NAACL-HLT (1) (2019)
Keyphrases
  • co occurrence
  • biologically inspired
  • vector space
  • word sense
  • low dimensional
  • data sets
  • euclidean space
  • highly informative
  • pre attentive
  • computer vision
  • image sequences
  • n gram
  • visual attention