ACL Conf. on Empirical Methods in Natural Language Processing, EMNLP 2016


Article Details
Title: How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
Article URLs:
Alternative Article URLs:
Authors: Chia-Wei Liu
  • McGill University, School of Computer Science
Ryan Lowe
  • McGill University, School of Computer Science
Iulian Serban
  • Université de Montréal, DIRO
Michael Noseworthy
  • McGill University, School of Computer Science
Laurent Charlin
  • McGill University, School of Computer Science
Joelle Pineau
  • McGill University, School of Computer Science
Sharing: Unknown
Verification: Authors have not verified information
Artifact Evaluation Badge: none
Artifact URLs:
Artifact Correspondence Email Addresses:
NSF Award Numbers:
DBLP Key: conf/emnlp/LiuLSNCP16
Author Comments:

Discuss this paper and its artifacts below