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: ACL (Findings) (2022)
Keyphrases
  • probabilistic model
  • training set
  • data sets
  • machine learning
  • learning algorithm
  • feature selection
  • pairwise
  • prior knowledge
  • domain knowledge
  • training examples
  • learning models