In this paper, we describe our method for ranking the skills required for a given job title. Our analysis shows that important/relevant skills appear more frequently in similar job titles. We train a Language-agnostic BERT Sentence Encoder (LaBSE) model to predict the importance of the skills using weak supervision. We show the model can learn the importance of skills and perform well in other languages. Furthermore, we show how the Inverse Document Frequency factor of skill boosts the specialised skills.
@article{arxiv.2212.08553,
title = {Is it Required? Ranking the Skills Required for a Job-Title},
author = {Sarthak Anand and Jens-Joris Decorte and Niels Lowie},
journal= {arXiv preprint arXiv:2212.08553},
year = {2022}
}