Towards an Integrated Retrieval System to Semantically Match CVs, Job Descriptions and Curricula

Abstract

The job market is continuously evolving. The specific occupations, skills, competences and qualifications that people need change over time, as does their description. To deal with this, effective and intelligent communication and information exchange between the job market and the education and training sector is vital. On the other hand, and from the perspective of the individual (job seeker), especially the less privileged there is a need for approaches that combine practical tools with motivation and mentoring support since skill-matching it is not enough, skill-building is also needed. In this context, the current approach follows a bottom-up methodology investigating the problem of formalizing the lifelong learning process in a dynamic and flexible way. On the other hand, this proposal utilizes a parallel top-down approach in applying semantics and standards upon data in order to alleviate the gap among individuals, workplaces and educational contexts for the benefit of all in a transparent way. More specifically, this article reports towards an approach on tackling the complex task of interconnecting job seekers, employers and educational agents in the current European labor market. To perform this task, we implement an end-to-end service to parse resumes, job descriptions and open courses descriptions, retrieve information on the qualifications associated with the aforementioned, and semantically match them. The proposed implementation effectively detects the underlying information associated with those sources, and manages to interlink job seekers’ resumes to occupations and job vacancies, while being able to assign skill deficits to courses provided by educational agents. The performance of our implementation on CVs, job descriptions and course descriptions in English, Greek, Romanian and Bulgarian, indicate that our approach yields results on par with the state-of-the-art, however on a much larger scale: to the best of our knowledge, this is the first research work that engages with this task on three stakeholders (job seekers, employers, educational agents) and in four European languages.