Information extraction method from resume

Abstract

An approach to information extraction from short and poorly structured text document such as resume (CV) is suggested. The computer-based resume processing is an actual interesting application problem. There are a number of web-sites for centralized CVs allocation oriented at different employers. Oftenly, an employer is most interested in some peculiar features connected to professional achievements and knowledges of the applicant, not a resume as a whole. Extraction of such peculiar information from CV is a problem itself especially if the CV is organized in an arbitrary form, poorly structured and contains grammatic mistakes. The suggested paper is devoted to processsing the CVs of this type. A short review is given of the existing approaches to information extraction from CV and the key-word-based approach is selected and founded from the viewpoint of efficient information extraction the employer is interested in. The specificity of the approach is emphasized for the case when keywords define text blocks with a definite conceptual content. In this case one more problem arrises connected to text blocks definition. An approach based on clustering technique is suggested, so each cluster is associated with the corresponding text block in the raw CV. At the same time, the technical realization of the approach suggested remains open for future investigations. The examples are given illustrating text extraction technique to get a relevant answer to arbitrary employer query addressed to CV.