@article{guo-etal-2024-deuce,
    title = "{DEUCE}: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learning",
    author = "Guo, Jiaxin  and
      Chen, C. L. Philip  and
      Li, Shuzhen  and
      Zhang, Tong",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "12",
    year = "2024",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.tacl-1.94/",
    doi = "10.1162/tacl_a_00731",
    pages = "1736--1754",
    abstract = "Cold-start active learning (CSAL) selects valuable instances from an unlabeled dataset for manual annotation. It provides high-quality data at a low annotation cost for label-scarce text classification. However, existing CSAL methods overlook weak classes and hard representative examples, resulting in biased learning. To address these issues, this paper proposes a novel dual-diversity enhancing and uncertainty-aware (DEUCE) framework for CSAL. Specifically, DEUCE leverages a pretrained language model (PLM) to efficiently extract textual representations, class predictions, and predictive uncertainty. Then, it constructs a Dual-Neighbor Graph (DNG) to combine information on both textual diversity and class diversity, ensuring a balanced data distribution. It further propagates uncertainty information via density-based clustering to select hard representative instances. DEUCE performs well in selecting class-balanced and hard representative data by dual-diversity and informativeness. Experiments on six NLP datasets demonstrate the superiority and efficiency of DEUCE."
}