# SkillSpan: Hard and Soft Skill Extraction from English Job Postings Source: [SkillSpan: Hard and Soft Skill Extraction from English Job Postings]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:10:48.263Z Authors: Mike Zhang, Kristian N{\\o}rgaard Jensen, Sif Dam Sonniks, Barbara Plank Published: 2022-04-27T10:07:36.000Z ## Abstract Skill Extraction (SE) 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, we introduce SKILLSPAN, a novel SE dataset consisting of 14.5K sentences and over 12.5K annotated spans. We release its respective guidelines created over three different sources annotated for hard and soft skills by domain experts. We introduce a BERT baseline (Devlin et al., 2019). To improve upon this baseline, we experiment with language models that are optimized for long spans (Joshi et al., 2020; Beltagy et al., 2020), continuous pre-training on the job posting domain (Han and Eisenstein, 2019; Gururangan et al., 2020), and multi-task learning (Caruana, 1997). Our results show that the domain-adapted models significantly outperform their non-adapted counterparts, and single-task outperforms multi-task learning. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Sequence Labeling on SKILLSPAN English (test)](): Sequence Labeling; SKILLSPAN English (test); Span-F1: 58.9. ## Original sources and implementation [Original paper]() [PDF]()