@inproceedings{strout-etal-2019-human,
    title = "Do Human Rationales Improve Machine Explanations?",
    author = "Strout, Julia  and
      Zhang, Ye  and
      Mooney, Raymond",
    editor = "Linzen, Tal  and
      Chrupa{\l}a, Grzegorz  and
      Belinkov, Yonatan  and
      Hupkes, Dieuwke",
    booktitle = "Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/W19-4807/",
    doi = "10.18653/v1/W19-4807",
    pages = "56--62",
    abstract = "Work on {\textquotedblleft}learning with rationales{\textquotedblright} shows that humans providing explanations to a machine learning system can improve the system`s predictive accuracy. However, this work has not been connected to work in {\textquotedblleft}explainable AI{\textquotedblright} which concerns machines explaining their reasoning to humans. In this work, we show that learning with rationales can also improve the quality of the machine`s explanations as evaluated by human judges. Specifically, we present experiments showing that, for CNN-based text classification, explanations generated using {\textquotedblleft}supervised attention{\textquotedblright} are judged superior to explanations generated using normal unsupervised attention."
}