®®®® SIIA Público

Título del libro: Optimal Energy Growth In Variable-Density Mixing Layers At High Atwood Number
Título del capítulo: SegCV: traitement efficace de CV avec analyse et correction d?erreurs

Autores UNAM:
JUAN MANUEL TORRES MORENO;
Autores externos:

Idioma:
Inglés
Año de publicación:
2013
Palabras clave:

Algoritms; Amount of information; Automatic parsing; Correction of errors; CV parsing; Exponential growth; Free style; Online markets; Plain text; Rule modeling; Surface analysis


Resumen:

Over the last years, the online market of jobs and candidatures offers has reached an exponential growth. This has implied great amounts of information (mainly in a text free style) which cannot be processed manually. The résumés are in several formats: .pdf, .doc, .dvi, .ps, etc., that can provoque errors or noise during the conversion to plain text. We propose SegCV, a system that has as goal the automatic parsing of candidates? résumés. In this article we present the algoritms, which are based over a surface analysis, to segment the résumés in an accurate way. We evaluated the automatic segmentation using a reference corpus that we have created. The preliminary experiments, done over a large collection of résumés in French with noise correction, show good results in precision, recall and F-score. © 2013 Proceedings of TALN. All rights reserved.


Entidades citadas de la UNAM: