@inproceedings{loukina-etal-2020-using,
    title = "Using {PRMSE} to evaluate automated scoring systems in the presence of label noise",
    author = "Loukina, Anastassia  and
      Madnani, Nitin  and
      Cahill, Aoife  and
      Yao, Lili  and
      Johnson, Matthew S.  and
      Riordan, Brian  and
      McCaffrey, Daniel F.",
    booktitle = "Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications",
    month = jul,
    year = "2020",
    address = "Seattle, WA, USA → Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2020.bea-1.2",
    doi = "10.18653/v1/2020.bea-1.2",
    pages = "18--29",
    abstract = "The effect of noisy labels on the performance of NLP systems has been studied extensively for system training. In this paper, we focus on the effect that noisy labels have on system evaluation. Using automated scoring as an example, we demonstrate that the quality of human ratings used for system evaluation have a substantial impact on traditional performance metrics, making it impossible to compare system evaluations on labels with different quality. We propose that a new metric, PRMSE, developed within the educational measurement community, can help address this issue, and provide practical guidelines on using PRMSE.",
}