@inproceedings{africa-etal-2025-meta,
    title = "Meta-Pretraining for Zero-Shot Cross-Lingual Named Entity Recognition in Low-Resource {P}hilippine Languages",
    author = "Africa, David Demitri  and
      Salhan, Suchir  and
      Weiss, Yuval  and
      Buttery, Paula  and
      Diehl Martinez, Richard",
    editor = "Adelani, David Ifeoluwa  and
      Arnett, Catherine  and
      Ataman, Duygu  and
      Chang, Tyler A.  and
      Gonen, Hila  and
      Raja, Rahul  and
      Schmidt, Fabian  and
      Stap, David  and
      Wang, Jiayi",
    booktitle = "Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025)",
    month = nov,
    year = "2025",
    address = "Suzhuo, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.mrl-main.8/",
    pages = "106--127",
    ISBN = "979-8-89176-345-6",
    abstract = "Named-entity recognition (NER) in low-resource languages is usually tackled by finetuning very large multilingual LMs, an option that is often infeasible in memory- or latency-constrained settings. We ask whether small decoder LMs can be pretrained so that they adapt quickly and transfer zero-shot to languages unseen during pretraining. To this end we replace part of the autoregressive objective with first-order model-agnostic meta-learning (MAML). Tagalog and Cebuano are typologically similar yet structurally different in their actor/non-actor voice systems, and hence serve as a challenging test-bed. Across four model sizes (11 M {--} 570 M) MAML lifts zero-shot micro-F1 by 2{--}6 pp under head-only tuning and 1{--}3 pp after full tuning, while cutting convergence time by up to 8{\%}. Gains are largest for single-token person entities that co-occur with Tagalog case particles si/ni, highlighting the importance of surface anchors."
}