@inproceedings{anderson-2024-exploring-language,
    title = "Exploring Language Representation through a Resource Inventory Project",
    author = "Anderson, Carolyn",
    editor = {Al-azzawi, Sana  and
      Biester, Laura  and
      Kov{\'a}cs, Gy{\"o}rgy  and
      Marasovi{\'c}, Ana  and
      Mathur, Leena  and
      Mieskes, Margot  and
      Weissweiler, Leonie},
    booktitle = "Proceedings of the Sixth Workshop on Teaching NLP",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.teachingnlp-1.14/",
    pages = "91--93",
    abstract = "The increasing scale of large language models has led some students to wonder what contributions can be made in academia. However, students are often unaware that LLM-based approaches are not feasible for the majority of the world`s languages due to lack of data availability. This paper presents a research project in which students explore the issue of language representation by creating an inventory of the data, preprocessing, and model resources available for a less-resourced language. Students are put into small groups and assigned a language to research. Within the group, students take on one of three roles: dataset investigator, preprocessing investigator, or downstream task investigator. Students then work together to create a 7-page research report about their language."
}