Improving Online Job Advertisement Analysis via Compositional Entity Extraction

ACL ARR 2025 May Submission4061 Authors

Abstract: We propose a compositional entity modeling framework for requirement extraction from online job advertisements (OJAs), representing complex, tree-like structures that connect atomic entities via typed relations. Based on this schema, we introduce GOJA, a manually annotated dataset of 500 German job ads that captures roles, tools, experience levels, attitudes, and their functional context. We report strong inter-annotator agreement and benchmark transformer models, demonstrating the feasibility of learning this structure. A focused case study on AI-related requirements illustrates the analytical value of our approach for labor market research.

Paper Type: Long

Research Area: Information Extraction

Research Area Keywords: Computational Social Science, Information Extraction

Contribution Types: Data resources, Data analysis

Languages Studied: German

Submission Number: 4061