Is it Required? Ranking the Skills Required for a Job-Title
Sarthak Anand, Jens-Joris Decorte, Niels Lowie
TL;DR
This paper presents a multilingual method for ranking job skills using a BERT-based model trained with weak supervision, highlighting the importance of skills and the impact of frequency factors across similar job titles.
Contribution
It introduces a language-agnostic BERT model for skill importance ranking and demonstrates its effectiveness across languages and the influence of frequency-based skill boosting.
Findings
Model effectively predicts skill importance across languages
Frequency factors enhance the ranking of specialized skills
Skills appear more relevant in similar job titles
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Text Readability and Simplification
MethodsMulti-Head Attention · Attention Is All You Need · Linear Layer · Dense Connections · Attention Dropout · Residual Connection · Refunds@Expedia|||How do I get a full refund from Expedia? · Weight Decay · WordPiece · Linear Warmup With Linear Decay