Remy Kessler

The exponential growth of the Internet has made the development of a market of on-line job search sites possible. This paper aims at presenting the E-Gen system (Automatic Job Offer Processing system for Human Resources). E-Gen will implement two complex tasks: an analysis and categorisation of job postings, which are unstructured text documents (e-mails of job listings, possibly with an attached document), an analysis and a relevance ranking of the candidate's answers (cover letter and curriculum vitae). This paper aims to present a strategy to resolve the first task: after a process of filtering and lemmatisation, we use vectorial representation before generating a classification with Support Vector Machines and n-grams of words. This first classification is then transmitted to a "corrective" post-process (with the Markov model and a Branch&Bound algorithm for pruning the tree) which improves the quality of the solution.

The market of online job search sites grows exponentially. This implies volumes of information (mostly in the form of free text) become manually impossible to process. An analysis and assisted categorization seems relevant to address this issue. We present E-Gen, a system which aims to perform assisted analysis and categorization of job offers and of the responses of candidates. This

ABSTRACT The evolution of the job market has resulted in traditional methods of recruitment becoming insufficient. As it is now necessary to handle volumes of information (mostly in the form of free text) that are impossible to process manually, an analysis and assisted categorization are essential to address this issue. In this paper, we present a combination of the E-Gen and Cortex systems. E-Gen aims to perform analysis and categorization of job offers together with the responses given by the candidates. E-Gen system strategy is based on vectorial and probabilistic models to solve the problem of profiling applications according to a specific job offer. Cortex is a statistical automatic summarization system. In this work, E-Gen uses Cortex as a powerful filter to eliminate irrelevant information contained in candidate answers. Our main objective is to develop a system to assist a recruitment consultant and the results obtained by the proposed combination surpass those of E-Gen in standalone mode on this task.

The exponential growth of the Internet has made the development of a market of on-line job search sites possible. This paper aims at presenting the E-Gen system (Automatic Job Offer Processing system for Human Resources). E-Gen will implement two complex tasks: an analysis and categorisation of job postings, which are unstructured text documents (e-mails of job listings, possibly with an attached document), an analysis and a relevance ranking of the candidate's answers (cover letter and curriculum vitae). This paper aims to present a strategy to resolve the first task: after a process of filtering and lemmatisation, we use vectorial representation before generating a classification with Support Vector Machines and n-grams of words. This first classification is then transmitted to a "corrective" post-process (with the Markov model and a Branch&Bound algorithm for pruning the tree) which improves the quality of the solution.

Introduction Méthodes de classification automatique Implémentation Évaluation Conclusion Choix expérimentaux Analyse des corpus ... Classification en genre et en th`eme ... Comment s'attaquer au probl`eme ? 7 participants pour l'équipe jeunes chercheurs Choix communs ...