Login / Signup

Reminding the incremental language model via data-free self-distillation.

Han WangRuiliu FuChengzhang LiXuejun ZhangJun ZhouXing BaiYonghong YanQingwei Zhao
Published in: Appl. Intell. (2023)
Keyphrases
  • language model
  • mixture model
  • language modeling
  • prior knowledge
  • probability distribution
  • query expansion
  • statistical machine translation
  • discrete data