Login / Signup

Improving the Out-Of-Distribution Generalization Capability of Language Models: Counterfactually-Augmented Data is not Enough.

Caoyun FanWenqing ChenJidong TianYitian LiHao HeYaohui Jin
Published in: CoRR (2023)
Keyphrases
  • language model
  • co occurrence
  • document retrieval
  • machine learning
  • n gram
  • training data
  • knowledge discovery
  • mixture model
  • document collections
  • speech recognition
  • test collection