arxivst stuff from arxiv that you should probably bookmark

Improving Semantic Composition with Offset Inference

Abstract · Apr 21, 2017 19:47 ·

apts distributional apt lexeme occurrences lexemes white composition cs-cl

Arxiv Abstract

  • Thomas Kober
  • Julie Weeds
  • Jeremy Reffin
  • David Weir

Count-based distributional semantic models suffer from sparsity due to unobserved but plausible co-occurrences in any text collection. This problem is amplified for models like Anchored Packed Trees (APTs), that take the grammatical type of a co-occurrence into account. We therefore introduce a novel form of distributional inference that exploits the rich type structure in APTs and infers missing data by the same mechanism that is used for semantic composition.

Read the paper (pdf) »