Skill Extraction from Job Postings using Weak Supervision

Mike Zhang; Kristian Nørgaard Jensen; Rob van der Goot; Barbara Plank

doi:10.48550/arXiv.2209.08071

Skill Extraction from Job Postings using Weak Supervision

Mike Zhang, Kristian Nørgaard Jensen, Rob van der Goot, Barbara Plank

Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

Abstract

Aggregated data obtained from job postings provide powerful insights into labor market demands, and emerging skills, and aid job matching. However, most extraction approaches are supervised and thus need costly and time-consuming annotation. To overcome this, we propose Skill Extraction with Weak Supervision. We leverage the European Skills, Competences, Qualifications and Occupations taxonomy to find similar skills in job ads via latent representations. The method shows a strong positive signal, outperforming baselines based on token-level and syntactic patterns.

Originalsprog	Engelsk
Titel	RecSys in HR'22: The 2nd Workshop on Recommender Systems for Human Resources, in conjunction with the 16th ACM Conference on Recommender Systems, September 18--23, 2022, Seattle, USA.
Forlag	CEUR Workshop Proceedings
Publikationsdato	19 sep. 2022
DOI	https://doi.org/10.48550/arXiv.2209.08071
Status	Udgivet - 19 sep. 2022

Emneord

Labor market demands
Emerging skills
Weak supervision
Skill extraction
Latent representations

Adgang til dokumentet

10.48550/arXiv.2209.08071

RecSysHR2022-paper_10Forlagets udgivne version, 660 KB

http://ceur-ws.org/Vol-3218/RecSysHR2022-paper_10.pdf

Citationsformater

Zhang, M., Jensen, K. N., van der Goot, R., & Plank, B. (2022). Skill Extraction from Job Postings using Weak Supervision. I RecSys in HR'22: The 2nd Workshop on Recommender Systems for Human Resources, in conjunction with the 16th ACM Conference on Recommender Systems, September 18--23, 2022, Seattle, USA. CEUR Workshop Proceedings. https://doi.org/10.48550/arXiv.2209.08071

@inproceedings{4735afc64ec5480da8060c23dd07bd04,

title = "Skill Extraction from Job Postings using Weak Supervision",

abstract = "Aggregated data obtained from job postings provide powerful insights into labor market demands, and emerging skills, and aid job matching. However, most extraction approaches are supervised and thus need costly and time-consuming annotation. To overcome this, we propose Skill Extraction with Weak Supervision. We leverage the European Skills, Competences, Qualifications and Occupations taxonomy to find similar skills in job ads via latent representations. The method shows a strong positive signal, outperforming baselines based on token-level and syntactic patterns.",

keywords = "Labor market demands, Emerging skills, Weak supervision, Skill extraction, Latent representations, Labor market demands, Emerging skills, Weak supervision, Skill extraction, Latent representations",

author = "Mike Zhang and Jensen, {Kristian N{\o}rgaard} and {van der Goot}, Rob and Barbara Plank",

year = "2022",

month = sep,

day = "19",

doi = "10.48550/arXiv.2209.08071",

language = "English",

booktitle = "RecSys in HR'22: The 2nd Workshop on Recommender Systems for Human Resources, in conjunction with the 16th ACM Conference on Recommender Systems, September 18--23, 2022, Seattle, USA.",

publisher = "CEUR Workshop Proceedings",

}

Skill Extraction from Job Postings using Weak Supervision. / Zhang, Mike; Jensen, Kristian Nørgaard; van der Goot, Rob et al.
RecSys in HR'22: The 2nd Workshop on Recommender Systems for Human Resources, in conjunction with the 16th ACM Conference on Recommender Systems, September 18--23, 2022, Seattle, USA.. CEUR Workshop Proceedings, 2022.

Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

TY - GEN

T1 - Skill Extraction from Job Postings using Weak Supervision

AU - Zhang, Mike

AU - Jensen, Kristian Nørgaard

AU - van der Goot, Rob

AU - Plank, Barbara

PY - 2022/9/19

Y1 - 2022/9/19

N2 - Aggregated data obtained from job postings provide powerful insights into labor market demands, and emerging skills, and aid job matching. However, most extraction approaches are supervised and thus need costly and time-consuming annotation. To overcome this, we propose Skill Extraction with Weak Supervision. We leverage the European Skills, Competences, Qualifications and Occupations taxonomy to find similar skills in job ads via latent representations. The method shows a strong positive signal, outperforming baselines based on token-level and syntactic patterns.

AB - Aggregated data obtained from job postings provide powerful insights into labor market demands, and emerging skills, and aid job matching. However, most extraction approaches are supervised and thus need costly and time-consuming annotation. To overcome this, we propose Skill Extraction with Weak Supervision. We leverage the European Skills, Competences, Qualifications and Occupations taxonomy to find similar skills in job ads via latent representations. The method shows a strong positive signal, outperforming baselines based on token-level and syntactic patterns.

KW - Labor market demands

KW - Emerging skills

KW - Weak supervision

KW - Skill extraction

KW - Latent representations

KW - Labor market demands

KW - Emerging skills

KW - Weak supervision

KW - Skill extraction

KW - Latent representations

U2 - 10.48550/arXiv.2209.08071

DO - 10.48550/arXiv.2209.08071

M3 - Article in proceedings

BT - RecSys in HR'22: The 2nd Workshop on Recommender Systems for Human Resources, in conjunction with the 16th ACM Conference on Recommender Systems, September 18--23, 2022, Seattle, USA.

PB - CEUR Workshop Proceedings

ER -

Skill Extraction from Job Postings using Weak Supervision

Abstract

Emneord

Adgang til dokumentet

Fingeraftryk

Citationsformater