构建技能关联性评估基准，提升人才推荐系统准确性
SkillMatch: Evaluating Self-supervised Learning of Skill Relatedness
- 基于百万职位广告中的技能共现，自监督训练句向量模型
- 新方法在技能关联性任务上显著超越传统模型
- 适合人力资源与推荐系统研究者使用
准确建模技能间关系是招聘与员工发展中的关键环节，但目前缺乏直接评估此类方法的基准。本文基于百万份职位广告中挖掘的专家知识，构建并发布SkillMatch基准，用于技能关联性任务。同时提出一种可扩展的自监督学习方法，基于职位广告中的技能共现来适配Sentence-BERT模型。该方法在SkillMatch上的表现远超传统模型。通过公开发布SkillMatch，旨在为提升技能推荐系统的准确性与透明性奠定基础。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。