@inproceedings{nekvinda-dusek-2021-shades,
    title = "Shades of {BLEU}, Flavours of Success: The Case of {M}ulti{WOZ}",
    author = "Nekvinda, Tom{\'a}{\v{s}}  and
      Du{\v{s}}ek, Ond{\v{r}}ej",
    editor = "Bosselut, Antoine  and
      Durmus, Esin  and
      Gangal, Varun Prashant  and
      Gehrmann, Sebastian  and
      Jernite, Yacine  and
      Perez-Beltrachini, Laura  and
      Shaikh, Samira  and
      Xu, Wei",
    booktitle = "Proceedings of the First Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2021.gem-1.4/",
    doi = "10.18653/v1/2021.gem-1.4",
    pages = "34--46",
    abstract = "The MultiWOZ dataset (Budzianowski et al.,2018) is frequently used for benchmarkingcontext-to-response abilities of task-orienteddialogue systems. In this work, we identifyinconsistencies in data preprocessing and re-porting of three corpus-based metrics used onthis dataset, i.e., BLEU score and Inform {\&}Success rates. We point out a few problemsof the MultiWOZ benchmark such as unsat-isfactory preprocessing, insufficient or under-specified evaluation metrics, or rigid database. We re-evaluate 7 end-to-end and 6 policy opti-mization models in as-fair-as-possible setups,and we show that their reported scores cannotbe directly compared. To facilitate compari-son of future systems, we release our stand-alone standardized evaluation scripts. We alsogive basic recommendations for corpus-basedbenchmarking in future works."
}