Annotated Job Ads with Named Entity Recognition

TL;DR

This paper presents a fine-tuned KB-BERT model for Swedish job ad NER, highlighting annotation strategies and demonstrating its effectiveness in extracting useful information from job postings.

Contribution

It introduces a new annotated dataset for Swedish job ads and details methods to improve annotation efficiency and quality.

Findings

High NER model performance on Swedish job ads

Effective annotation process for high-quality data

Demonstrated utility in extracting job-related information

Abstract

We have trained a named entity recognition (NER) model that screens Swedish job ads for different kinds of useful information (e.g. skills required from a job seeker). It was obtained by fine-tuning KB-BERT. The biggest challenge we faced was the creation of a labelled dataset, which required manual annotation. This paper gives an overview of the methods we employed to make the annotation process more efficient and to ensure high quality data. We also report on the performance of the resulting model.