Shades of BLEU, Flavours of Success: The Case of MultiWOZ
Tomáš Nekvinda, Ondřej Dušek · 2021
The MultiWOZ dataset (Budzianowski et al., 2018) is frequently used for benchmarking context-to-response abilities of task-oriented dialogue systems.In this work, we identify inconsistencies in data preprocessing and reporting of three corpus-based metrics used on this dataset, i.e., BLEU score and Inform & Success rates.We point out a few problems of the MultiWOZ benchmark such as unsatisfactory preprocessing, insufficient or underspecified evaluation metrics, or rigid database.We re-evaluate 7 end-to-end and 6 policy optimization models in as-fair-as-possible setups, and we show that their reported scores cannot be directly compared.To facilitate comparison of future systems, we release our standalone standardized evaluation scripts.We also give basic recommendations for corpus-based benchmarking in future works. 1 https://github.com/Tomiinek/MultiWOZ_ Evaluation