SkillMatch: Evaluating Self-supervised Learning of Skill Relatedness
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913535562350592 |
|---|---|
| author | Decorte, Jens-Joris Van Hautte, Jeroen Demeester, Thomas Develder, Chris |
| author_facet | Decorte, Jens-Joris Van Hautte, Jeroen Demeester, Thomas Develder, Chris |
| contents | Accurately modeling the relationships between skills is a crucial part of human resources processes such as recruitment and employee development. Yet, no benchmarks exist to evaluate such methods directly. We construct and release SkillMatch, a benchmark for the task of skill relatedness, based on expert knowledge mining from millions of job ads. Additionally, we propose a scalable self-supervised learning technique to adapt a Sentence-BERT model based on skill co-occurrence in job ads. This new method greatly surpasses traditional models for skill relatedness as measured on SkillMatch. By releasing SkillMatch publicly, we aim to contribute a foundation for research towards increased accuracy and transparency of skill-based recommendation systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_05006 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SkillMatch: Evaluating Self-supervised Learning of Skill Relatedness Decorte, Jens-Joris Van Hautte, Jeroen Demeester, Thomas Develder, Chris Computation and Language Accurately modeling the relationships between skills is a crucial part of human resources processes such as recruitment and employee development. Yet, no benchmarks exist to evaluate such methods directly. We construct and release SkillMatch, a benchmark for the task of skill relatedness, based on expert knowledge mining from millions of job ads. Additionally, we propose a scalable self-supervised learning technique to adapt a Sentence-BERT model based on skill co-occurrence in job ads. This new method greatly surpasses traditional models for skill relatedness as measured on SkillMatch. By releasing SkillMatch publicly, we aim to contribute a foundation for research towards increased accuracy and transparency of skill-based recommendation systems. |
| title | SkillMatch: Evaluating Self-supervised Learning of Skill Relatedness |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.05006 |