@inproceedings{pang-etal-2022-divide,
    title = "Divide and Denoise: Learning from Noisy Labels in Fine-Grained Entity Typing with Cluster-Wise Loss Correction",
    author = "Pang, Kunyuan  and
      Zhang, Haoyu  and
      Zhou, Jie  and
      Wang, Ting",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2022.acl-long.141/",
    doi = "10.18653/v1/2022.acl-long.141",
    pages = "1997--2006",
    abstract = "Fine-grained Entity Typing (FET) has made great progress based on distant supervision but still suffers from label noise. Existing FET noise learning methods rely on prediction distributions in an instance-independent manner, which causes the problem of confirmation bias. In this work, we propose a clustering-based loss correction framework named Feature Cluster Loss Correction (FCLC), to address these two problems. FCLC first train a coarse backbone model as a feature extractor and noise estimator. Loss correction is then applied to each feature cluster, learning directly from the noisy labels. Experimental results on three public datasets show that FCLC achieves the best performance over existing competitive systems. Auxiliary experiments further demonstrate that FCLC is stable to hyperparameters and it does help mitigate confirmation bias. We also find that in the extreme case of no clean data, the FCLC framework still achieves competitive performance."
}