Login / Signup

Integrated Directional Gradients: Feature Interaction Attribution for Neural NLP Models.

Sandipan SikdarParantapa BhattacharyaKieran Heese
Published in: ACL/IJCNLP (1) (2021)
Keyphrases
  • neural network
  • multiscale
  • statistical model
  • statistical models
  • prior knowledge
  • natural language processing
  • text mining
  • neural models
  • information extraction
  • human computer interaction