@inproceedings{parde-nielsen-2017-finding,
    title = "Finding Patterns in Noisy Crowds: Regression-based Annotation Aggregation for Crowdsourced Data",
    author = "Parde, Natalie  and
      Nielsen, Rodney",
    editor = "Palmer, Martha  and
      Hwa, Rebecca  and
      Riedel, Sebastian",
    booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/D17-1204/",
    doi = "10.18653/v1/D17-1204",
    pages = "1907--1912",
    abstract = "Crowdsourcing offers a convenient means of obtaining labeled data quickly and inexpensively. However, crowdsourced labels are often noisier than expert-annotated data, making it difficult to aggregate them meaningfully. We present an aggregation approach that learns a regression model from crowdsourced annotations to predict aggregated labels for instances that have no expert adjudications. The predicted labels achieve a correlation of 0.594 with expert labels on our data, outperforming the best alternative aggregation method by 11.9{\%}. Our approach also outperforms the alternatives on third-party datasets."
}