Elamur Research⌕
☰
home / papers / 2026 / Skill Extraction from Resumes and Job Offers across Six Languages

Skill Extraction from Resumes and Job Offers across Six Languages

Paper · 2026 · Laura Vásquez-Rodríguez, Bertrand Audrin, Samuel Michel et al.

Summary

Automatic skill detection is central to applicant tracking systems. Prior research, however, mostly covers job ads in a few languages, narrow domains and hard skills only, because resumes are privacy-sensitive and annotation is costly. Within the Swiss SEM24 Innosuisse project, the authors built a gold-standard set of 1,200 real documents from their HR-tech partner (Arca24). It contains 100 resumes and 100 job offers in each of English, French, German, Italian, Spanish and Portuguese, spanning roughly 45 domains. HR specialists labelled the documents using guidelines based on the KSAO framework, and the experiments concentrate on hard skills and occupations. The authors compare three approaches of increasing complexity:

  • rule-based matching against two taxonomies (ESCO_DB and a proprietary IN-HOUSE_DB),
  • semantic matching against the same taxonomies,
  • supervised fine-tuned models such as mBERT, also tested on the public Green job-ad dataset.

Supervised models perform best, reaching F1 of about 0.6. Taxonomy-based methods are less accurate but easier to explain. Skills are also worded quite differently in resumes than in job offers, so resumes and transparent multilingual pipelines deserve more research attention.

Key points

  • New corpus: 1,200 manually annotated documents (Arca24_JOB and Arca24_CV), split evenly across six languages and two document types. Four annotators produced the labels in Docanno, followed by an adjudication round.
  • Taxonomies:
    • ESCO_DB has 3,039 occupations and 13,939 skills in 28 languages; about 131,623 English entities were extracted from it.
    • IN-HOUSE_DB has 10,379 curated skill entities translated into more than 10 languages.
  • Results on the Green dataset: mBERT reaches an overall F1 of 0.418 with exact matching and 0.595 with partial matching.
  • Resumes vs. job offers: resumes contain many more entities than job offers, and their entity statistics vary considerably across languages.
  • Data availability: the proprietary resumes and job offers cannot be released. Non-proprietary data and models are announced for GitHub (idiap/multilingual_skill_extraction).

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 2The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 works

Cite

Cite as Laura Vásquez-Rodríguez, Bertrand Audrin, Samuel Michel, Samuele Galli, Julneth Rogenhofer, Jacopo Negro Cusa and Lonneke van der Plas. 2026. Skill Extraction from Resumes and Job Offers across Six Languages. Proceedings of the 11th Edition of the Swiss Text Analytics Conference.

The paper itself, not this page. BibTeX from the library's record of the work.

@inproceedings{vasquezrodriguez2026skill,
  title = {{Skill Extraction from Resumes and Job Offers across Six Languages}},
  author = {Laura Vásquez-Rodríguez, Bertrand Audrin, Samuel Michel, Samuele Galli, Julneth Rogenhofer, Jacopo Negro Cusa and Lonneke {van der Plas}},
  booktitle = {Proceedings of the 11th Edition of the Swiss Text Analytics Conference},
  year = {2026},
  url = {https://aclanthology.org/2026.swisstext-1.10/}
}

References

32 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. David G. Allen and James M. Vardaman. 2017. Recruitment and retention across cultures. Annual Review of Organizational Psychology and Organizational Behavior, 4(1):153–181. find
  2. David Beauchemin, Julien Laumonier, Yvan Ster, and Marouane Yassine. 2022. "fijo": a french insurance soft skill detection dataset. arXiv. find
  3. Akshay Bhola, Kishaloy Halder, Animesh Prasad, and Min-Yen Kan. 2020. Retrieving skills from job descriptions: A language model based extreme multi-label classification framework. In Proceedings of the 28th International Conference on Computational Linguistics, pages 5832–5842, Barcelona, Spain (Onl… find
  4. Roberto Boselli, Mirko Cesarini, Fabio Mercorio, and Mario Mezzanzanica. 2018. Classifying online job advertisements through machine learning. Future Generation Computer Systems, 86:319–328. find
  5. Michael A. Campion, Alexis A. Fink, Brian J. Rugge-berg, Linda Carr, Guy M. Phillips, and Ronald B. Odman. 2011. Doing competencies well: Best practices in competency modeling. Personnel Psychology, 64(1):225–262. find
  6. Benjamin Clavié and Guillaume Soulié. 2023. Large language models as batteries-included zero-shot esco skills matchers. In RecSys in HR’23: The 3rd Workshop on Recommender Systems for Human Resources, in conjunction with the 17th ACM Conference on Recommender Systems, September 18–22, 2023, Singapor… find
  7. Jens-Joris Decorte, Severine Verlinden, Jeroen Van Hautte, Johannes Deleu, Chris Develder, and Thomas Demeester. 2023. Extreme multi-label skill extraction training using large language models. In International Workshop on AI for Human Resources and Public Employment Services (AI4HR&PES) at ECML-PKD… find
  8. Alessandro Fabris, Nina Baranowska, Matthew J. Dennis, David Graus, Philipp Hacker, Jorge Saldivar, Frederik Zuiderveen Borgesius, and Asia J. Biega. 2025. Fairness and bias in algorithmic hiring: A multidisciplinary survey. ACM Trans. Intell. Syst. Technol., 16(1). find
  9. Chengguang Gan, Qinghao Zhang, and Tatsunori Mori. 2024. Application of llm agents in recruitment: A novel framework for resume screening. Preprint, arXiv:2401.08315. — [arXiv:2401.08315](https://arxiv.org/abs/2401.08315) find
  10. Ann-sophie Gnehm, Eva Bühlmann, Helen Buchs, and Simon Clematide. 2022. Fine-grained extraction and classification of skill requirements in German-speaking job ads. In Proceedings of the Fifth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS), pages 14–24, Abu Dhabi,… find
  11. Thomas Green, Diana Maynard, and Chenghua Lin. 2022. Development of a benchmark corpus to support entity recognition in job descriptions. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 1201–1208, Marseille, France. European Language Resources Association. find
  12. Akshay Gugnani and Hemant Misra. 2020. Implicit skills extraction using document embedding and its use in job recommendation. Proceedings of the AAAI Conference on Artificial Intelligence, 34(08):13286– 13293. find
  13. Shiqiang Guo, Folami Alamudun, and Tracy Hammond. 2016. Résumatcher: A personalized résumé-job matching system. Expert Systems with Applications, 60:169–182. find
  14. Elena Senger, Mike Zhang, Rob van der Goot, and Barbara Plank. 2024. Deep learning-based computational job market analysis: A survey on skill extraction and classification from job postings. In Proceedings of the First Workshop on Natural Language Processing for Human Resources (NLP4HR 2024), pages… find
  15. Damian A. Tamburri, Willem-Jan Van Den Heuvel, and Martin Garriga. 2020. Dataops for societal intelligence: a data pipeline for labor market skills extraction and matching. In 2020 IEEE 21st International Conference on Information Reuse and Integration for Data Science (IRI), pages 391–394. find
  16. Faizan Javed, Phuong Hoang, Thomas Mahoney, and Matt McNair. 2017. Large-scale occupational skills normalization for online recruitment. Proceedings of the AAAI Conference on Artificial Intelligence, 31(2):4627–4634. find
  17. Ilkka Kivimäki, Alexander Panchenko, Adrien Dessy, Dries Verdegem, Pascal Francq, Hugues Bersini, and Marco Saerens. 2013. A graph-based approach to skill extraction from text. In Proceedings of TextGraphs-8 Graph-based Methods for Natural Language Processing, pages 79–87, Seattle, Washington, USA.… find
  18. Sunil Kumar Kopparapu. 2010. Automatic extraction of usable information from unstructured resumes to aid search. In 2010 IEEE International Conference on Progress in Informatics and Computing, volume 1, pages 99–103. find
  19. VI Levenshtein. 1966. Binary codes capable of correcting deletions, insertions, and reversals. Proceedings of the Soviet physics doklady. find
  20. Nan Li, Bo Kang, and Tijl De Bie. 2023. Skillgpt: a restful api service for skill extraction and standardization using a large language model. In International Workshop on AI for Human Resources and Public Employment Services (AI4HR&PES) at ECML-PKDD. find
  21. Hiroki Nakayama, Takahiro Kubo, Junya Kamura, Yasufumi Taniguchi, and Xu Liang. 2018. doccano: Text annotation tool for human. Software available from https://github.com/doccano/doccano. ↗
  22. Khanh Nguyen, Mike Zhang, Syrielle Montariol, and Antoine Bosselut. 2024. Rethinking skill extraction in the job market domain using large language models. In Proceedings of the First Workshop on Natural Language Processing for Human Resources (NLP4HR 2024), pages 27–42, St. Julian’s, Malta. Associa… find
  23. Lance A Ramshaw and Mitchell P Marcus. 1999. Text chunking using transformation-based learning. In Natural language processing using very large corpora, pages 157–176. Springer. find
  24. Nils Reimers and Iryna Gurevych. 2020. Making monolingual sentence embeddings multilingual using knowledge distillation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4512–4525, Online. Association for Computational Linguistics.
  25. Laura Vásquez-Rodríguez, Bertrand Audrin, Samuel Michel, Samuele Galli, Julneth Rogenhofer, Jacopo Negro Cusa, and Lonneke Van Der Plas. 2024. Hardware-effective approaches for skill extraction in job offers and resumes. In RecSys in HR’24: The 4th Workshop on Recommender Systems for Human Resources… find
  26. Laura Vásquez-Rodríguez, Bertrand Audrin, Samuel Michel, Samuele Galli, Julneth Rogenhofer, Jacopo Negro Cusa, and Lonneke van der Plas. 2024. Hardware-effective approaches for skill extraction in job offers and resumes. In Proceedings of the 4th Workshop on Recommender Systems for Human Resources (… find
  27. Yinfei Yang, Daniel Cer, Amin Ahmad, Mandy Guo, Jax Law, Noah Constant, Gustavo Hernandez Abrego, Steve Yuan, Chris Tar, Yun-hsuan Sung, Brian Strope, and Ray Kurzweil. 2020. Multilingual universal sentence encoder for semantic retrieval. In Proceedings of the 58th Annual Meeting of the Association…
  28. Mike Zhang, Kristian Jensen, Sif Sonniks, and Barbara Plank. 2022a. SkillSpan: Hard and soft skill extraction from English job postings. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4962–4984,… find
  29. Mike Zhang, Kristian Nørgaard Jensen, and Barbara Plank. 2022b. Kompetencer: Fine-grained skill classification in Danish job postings via distant supervision and transfer learning. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 436–447, Marseille, France. Europe… find
  30. Mike Zhang, Kristian Nørgaard Jensen, Rob van der Goot, and Barbara Plank. 2022c. Skill extraction from job postings using weak supervision. In Rec-Sys in HR’22: The 2nd Workshop on Recommender Systems for Human Resources, in conjunction with the 16th ACM Conference on Recommender Systems, September… find
  31. Mike Zhang, Rob van der Goot, and Barbara Plank. 2023. ESCOXLM-R: Multilingual taxonomy-driven pre-training for the job market domain. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11871–11890, Toronto, Canada. Association f… find
  32. Meng Zhao, Faizan Javed, Ferosh Jacob, and Matt Mc-Nair. 2015. Skill: A system for skill identification and normalization. Proceedings of the AAAI Conference on Artificial Intelligence, 29(2):4012–4017. \#\# Acknowledgments We would like to thank Arca24 HR specialists for their support with annotation… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/rodriguez-2026-skill-extraction-resumes-job-offers/