Login / Signup

A Principled Framework for Evaluating Summarizers: Comparing Models of Summary Quality against Human Judgments.

Maxime PeyrardJudith Eckle-Kohler
Published in: ACL (2) (2017)
Keyphrases
  • human judgments
  • probabilistic model
  • high quality
  • artificial intelligence
  • active learning
  • low level
  • background knowledge
  • human subjects
  • automatic evaluation