Sign in

Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models.

Wenkai YangLei LiZhiyuan ZhangXuancheng RenXu SunBin He
Published in: NAACL-HLT (2021)
Keyphrases
  • probabilistic model
  • prior knowledge
  • statistical models
  • neural network
  • statistical model
  • data sets
  • information retrieval
  • feature space
  • high dimensional
  • natural language processing
  • co occurrence
  • vector space