@inproceedings{gelles-dunham-2024-multi,
    title = "Multi-Label Field Classification for Scientific Documents using Expert and Crowd-sourced Knowledge",
    author = "Gelles, Rebecca  and
      Dunham, James",
    editor = "Lucie-Aim{\'e}e, Lucie  and
      Fan, Angela  and
      Gwadabe, Tajuddeen  and
      Johnson, Isaac  and
      Petroni, Fabio  and
      van Strien, Daniel",
    booktitle = "Proceedings of the First Workshop on Advancing Natural Language Processing for Wikipedia",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.wikinlp-1.7/",
    doi = "10.18653/v1/2024.wikinlp-1.7",
    pages = "14--20",
    abstract = "Taxonomies of scientific research seek to describe complex domains of activity that are overlapping and dynamic. We address this challenge by combining knowledge curated by the Wikipedia community with the input of subject-matter experts to identify, define, and validate a system of 1,110 granular fields of study for use in multi-label classification of scientific publications. The result is capable of categorizing research across subfields of artificial intelligence, computer security, semiconductors, genetics, virology, immunology, neuroscience, biotechnology, and bioinformatics. We then develop and evaluate a solution for zero-shot classification of publications in terms of these fields."
}