@inproceedings{zhou-etal-2023-improving,
    title = "Improving Self-training for Cross-lingual Named Entity Recognition with Contrastive and Prototype Learning",
    author = "Zhou, Ran  and
      Li, Xin  and
      Bing, Lidong  and
      Cambria, Erik  and
      Miao, Chunyan",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.acl-long.222/",
    doi = "10.18653/v1/2023.acl-long.222",
    pages = "4018--4031",
    abstract = "In cross-lingual named entity recognition (NER), self-training is commonly used to bridge the linguistic gap by training on pseudo-labeled target-language data. However, due to sub-optimal performance on target languages, the pseudo labels are often noisy and limit the overall performance. In this work, we aim to improve self-training for cross-lingual NER by combining representation learning and pseudo label refinement in one coherent framework. Our proposed method, namely ContProto mainly comprises two components: (1) contrastive self-training and (2) prototype-based pseudo-labeling. Our contrastive self-training facilitates span classification by separating clusters of different classes, and enhances cross-lingual transferability by producing closely-aligned representations between the source and target language. Meanwhile, prototype-based pseudo-labeling effectively improves the accuracy of pseudo labels during training. We evaluate ContProto on multiple transfer pairs, and experimental results show our method brings substantial improvements over current state-of-the-art methods."
}