@inproceedings{liu-etal-2016-evaluate,
    title = "How {NOT} To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation",
    author = "Liu, Chia-Wei  and
      Lowe, Ryan  and
      Serban, Iulian  and
      Noseworthy, Mike  and
      Charlin, Laurent  and
      Pineau, Joelle",
    editor = "Su, Jian  and
      Duh, Kevin  and
      Carreras, Xavier",
    booktitle = "Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2016",
    address = "Austin, Texas",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/D16-1230/",
    doi = "10.18653/v1/D16-1230",
    pages = "2122--2132"
}