@inproceedings{wang-etal-2021-progressive,
    title = "Progressive Self-Training with Discriminator for Aspect Term Extraction",
    author = "Wang, Qianlong  and
      Wen, Zhiyuan  and
      Zhao, Qin  and
      Yang, Min  and
      Xu, Ruifeng",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2021.emnlp-main.23/",
    doi = "10.18653/v1/2021.emnlp-main.23",
    pages = "257--268",
    abstract = "Aspect term extraction aims to extract aspect terms from a review sentence that users have expressed opinions on. One of the remaining challenges for aspect term extraction resides in the lack of sufficient annotated data. While self-training is potentially an effective method to address this issue, the pseudo-labels it yields on unlabeled data could induce noise. In this paper, we use two means to alleviate the noise in the pseudo-labels. One is that inspired by the curriculum learning, we refine the conventional self-training to progressive self-training. Specifically, the base model infers pseudo-labels on a progressive subset at each iteration, where samples in the subset become harder and more numerous as the iteration proceeds. The other is that we use a discriminator to filter the noisy pseudo-labels. Experimental results on four SemEval datasets show that our model significantly outperforms the previous baselines and achieves state-of-the-art performance."
}