Login / Signup

On the Lack of Robust Interpretability of Neural Text Classifiers.

Muhammad Bilal ZafarMichele DoniniDylan SlackCédric ArchambeauSanjiv DasKrishnaram Kenthapadi
Published in: ACL/IJCNLP (Findings) (2021)
Keyphrases
  • information extraction
  • text classifiers
  • text classification
  • text categorization
  • natural language
  • neural network
  • data sets
  • labeled documents
  • feature space
  • knowledge representation
  • image features