@InProceedings{liu-EtAl:2016:EMNLP20163,
  author    = {Liu, Chia-Wei  and  Lowe, Ryan  and  Serban, Iulian  and  Noseworthy, Mike  and  Charlin, Laurent  and  Pineau, Joelle},
  title     = {How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation},
  booktitle = {Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing},
  month     = {November},
  year      = {2016},
  address   = {Austin, Texas},
  publisher = {Association for Computational Linguistics},
  pages     = {2122--2132},
  url       = {https://aclweb.org/anthology/D16-1230}
}