Login / Signup

Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models.

Aaron MuellerRobert FrankTal LinzenLuheng WangSebastian Schuster
Published in: CoRR (2022)
Keyphrases
  • prior knowledge
  • probabilistic model
  • machine learning algorithms
  • expert systems
  • model selection
  • training samples
  • training examples
  • bayesian framework