{"url":"/dataset/skillspan","name":"SkillSpan","full_name":"Hard and Soft Skill Extraction from English Job Postings","description_markdown":"**SkillSpan** is a dataset for Skill Extraction (SE). It is an important and widely-studied task useful to gain insights into labor market dynamics. However, there is a lacuna of datasets and annotation guidelines; available datasets are few and contain crowd-sourced labels on the span-level or labels from a predefined skill inventory. To address this gap, the authors introduce SkillSpan, a novel SE dataset consisting of 14.5K sentences and over 12.5K annotated spans.","description_withheld":null,"homepage":"https://github.com/kris927b/skillspan","introduced_date":"2022-04-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/skillspan-hard-and-soft-skill-extraction-from","title":"SkillSpan: Hard and Soft Skill Extraction from English Job Postings","first_author":"Mike Zhang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Multi-Task Learning","url":"/task/multi-task-learning","datasets_with_task":"/datasets/task/multi-task-learning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SkillSpan"],"data_loaders":[],"num_papers_in_archive":10,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}