Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a two-step approach to occupation coding that first employs a domain-specific Named Entity Recognition (NER) model to extract job titles from noisy text, followed by a focused mapping of these titles to occupational taxonomies. This separation of tasks enhances accuracy, robustness, and interpretability compared to traditional single-step methods. The approach, initially developed for German documents, is adaptable to other languages and incorporates a novel margin-based confidence criterion for improved coding reliability.
Separating job title extraction from taxonomy mapping boosts accuracy and interpretability in occupation coding, even in noisy text environments.
Occupation coding links job titles in free text to occupational taxonomies and is a core task in labor market research. Existing approaches typically address this problem in a single end-to-end step, jointly identifying job titles and assigning occupational codes. This paper presents a novel two-step approach that separates these tasks. In the first step, a domain-specific Named Entity Recognition (NER) model identifies occupational titles in continuous text, even under noise such as OCR errors. In the second step, the extracted job titles are mapped to a taxonomy, enabling the classifier to focus exclusively on this mapping. We demonstrate that this separation improves accuracy, robustness, and interpretability compared to single-step approaches. The method has been developed for German documents but is transferable to other languages. We further introduce a margin-based confidence criterion for occupation coding, replacing common absolute thresholds. To support reproducibility, we publish the source code and evaluation scripts.