@inproceedings{li-etal-2024-mcgill,
    title = "{M}c{G}ill {NLP} Group Submission to the {MRL} 2024 Shared Task: Ensembling Enhances Effectiveness of Multilingual Small {LM}s",
    author = "Li, Senyu  and
      Yu, Hao  and
      Ojo, Jessica  and
      Adelani, David Ifeoluwa",
    editor = {S{\"a}lev{\"a}, Jonne  and
      Owodunni, Abraham},
    booktitle = "Proceedings of the Fourth Workshop on Multilingual Representation Learning (MRL 2024)",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.mrl-1.28/",
    doi = "10.18653/v1/2024.mrl-1.28",
    pages = "346--356",
    abstract = "We present our systems for the three tasks and five languages included in the MRL 2024 Shared Task on Multilingual Multi-task Information Retrieval: (1) Named Entity Recognition, (2) Free-form Question Answering, and (3) Multiple-choice Question Answering. For each task, we explored the impact of selecting different multilingual language models for fine-tuning across various target languages, and implemented an ensemble system that generates final outputs based on predictions from multiple fine-tuned models. All models are large language models fine-tuned on task-specific data. Our experimental results show that a more balanced dataset would yield better results. However, when training data for certain languages are scarce, fine-tuning on a large amount of English data supplemented by a small amount of {\textquotedblleft}triggering data{\textquotedblright} in the target language can produce decent results."
}