@inproceedings{de-santo-etal-2026-skillens,
    title = "{S}ki{LL}ens: Recognising and Mapping Novel Skills from Millions of Job Ads Across {E}urope Using Language Models",
    author = "De Santo, Alessia  and
      Malandri, Lorenzo  and
      Mercorio, Fabio  and
      Mezzanzanica, Mario  and
      Nobani, Navid",
    editor = {Matusevych, Yevgen  and
      Eryi{\u{g}}it, G{\"u}l{\c{s}}en  and
      Aletras, Nikolaos},
    booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 5: Industry Track)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-industry.65/",
    pages = "877--885",
    ISBN = "979-8-89176-384-5",
    abstract = "In a rapidly evolving labor market, detecting and addressing emerging skill needs is essential for shaping responsive education and workforce policies. Online job advertisements (OJAs) provide a real-time view of changing demands, but require first retrieving skill mentions from unstructured text and then solving the entity linking problem of connecting them to standardized skill taxonomies. To harness this potential, we present a multilingual human-in-the-loop (HITL) pipeline that operates in two steps: candidate skills are extracted from national OJA corpora using country-specific word embeddings, capturing terms that reflect each country{'}s labor market. These candidates are linked to ESCO using an encoder-based system and refined through a decoder large language models (LLMs) for accurate contextual alignment. Our approach is validated through both quantitative and qualitative evaluations, demonstrating that our method enables timely, multilingual monitoring of emerging skills, supporting agile policy-making and targeted training initiatives."
}