Login / Signup

LightToken: A Task and Model-agnostic Lightweight Token Embedding Framework for Pre-trained Language Models.

Haoyu WangRuirui LiHaoming JiangZhengyang WangXianfeng TangBin BiMonica Xiao ChengBing YinYaqing WangTuo ZhaoJing Gao
Published in: KDD (2023)
Keyphrases
  • lightweight
  • probabilistic model
  • language model
  • statistical model
  • language modeling
  • relevance model
  • information retrieval
  • training data
  • em algorithm
  • n gram
  • test collection