arxivst stuff from arxiv that you should probably bookmark

Distributional model on a diet: One-shot word learning from text only

Abstract · Apr 14, 2017 22:29 ·

shot grounded contexts items distributional unknown text word erk cs-cl

Arxiv Abstract

  • Su Wang
  • Stephen Roller
  • Katrin Erk

We test whether distributional models can do one-shot learning of definitional properties from text only. Using Bayesian models, we find that first learning overarching structure in the known data, regularities in textual contexts and in properties, helps one-shot learning, and that individual context items can be highly informative.

Read the paper (pdf) »