Job Vacancy Ranking with Sentence Embeddings, Keywords, and Named Entities

Resume matching is the process of comparing a candidate’s curriculum vitae (CV) or resume with job description set employment requirements. The objective this procedure to assess degree which skills, qualifications, experience, and other relevant attributes align demands position. Some courses guide applicants in identifying key requirements within tailoring their experience highlight these aspects. Conversely, human resources (HR) specialists are trained extract critical information from numerous submitted resumes identify most suitable candidate for organization. An automated system typically employed compare text vacancies, providing score ranking indicate level similarity between two. However, can become time-consuming when dealing large number lengthy vacancy descriptions. In paper, we present dataset consisting software developers extracted public Telegram channel dedicated Israeli hi-tech applications. Additionally, propose natural language processing (NLP)-based approach that leverages neural sentence representations, keywords, named entities achieve state-of-the-art performance matching. We evaluate our using both automatic annotations demonstrate its superiority over leading resume–vacancy algorithm.