ACL 2022short9 citations

Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning

Miryam de Lhoneux, Sheng Zhang, Anders Søgaard

Abstract

Large multilingual pretrained language models such as mBERT and XLM-RoBERTa have been found to be surprisingly effective for cross-lingual transfer of syntactic parsing models Wu and Dredze (2019), but only between related languages. However, source and training languages are rarely related, when parsing truly low-resource languages. To close this gap, we adopt a method from multi-task learning, which relies on automated curriculum learning, to dynamically optimize for parsing performance on outlier languages. We show that this approach is significantly better than uniform and size-proportional sampling in the zero-shot setting.

BibTeX
@inproceedings{de-lhoneux-etal-2022-zero,
    title = "Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning",
    author = "de Lhoneux, Miryam  and
      Zhang, Sheng  and
      S{\o}gaard, Anders",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-short.64/",
    doi = "10.18653/v1/2022.acl-short.64",
    pages = "578--587"
}