User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

A Graph-Based Approach to Skill Extraction from Text

Primary tabs

download
  • Open access
  • PDF
  • 264.48 K
Panchenko, Alexander [UCL] Kivimäki, Ilkka [UCL] Dessy, Adrien [UCL] Verdegem, Dries [UCL] Francq, Pascal [UCL] Fairon, Cédrick [UCL] Saerens, Marco [UCL]

This paper presents a system that performs skill extraction from text documents. It outputs a list of professional skills that are relevant to a given input text. We argue that the system can be practical for hiring and management of personnel in an organization. We make use of the texts and the hyperlink graph of Wikipedia, as well as a list of professional skills obtained from the LinkedIn social network. The system is based on first computing similarities between an input document and the texts of Wikipedia pages and then using a biased, hub-avoiding version of the Spreading Activation algorithm on the Wikipedia graph in order to associate the input document with skills.

Document type Communication à un colloque (Conference Paper) – Présentation orale avec comité de sélection
Access type Accès libre
Publication date 2013
Language Anglais
Conference "TextGraphs-8 Graph-based Methods for Natural Language Processing", Seattle, USA (du 18/10/2013 au 19/10/2013)
Publication status Publié
Affiliations UCL - SSH/LouRIM - Louvain Research Institute in Management and Organizations
UCL - SSH/ILC - Institut Langage et Communication
UCL - SSH/TALN - Centre de traitement automatique du langage
UCL - SSH/ILC/PLIN - Pôle de recherche en linguistique
UCL - SST/ICTM - Institute of Information and Communication Technologies, Electronics and Applied Mathematics
Links
Bibliographic reference Panchenko, Alexander ; Kivimäki, Ilkka ; Dessy, Adrien ; Verdegem, Dries ; Francq, Pascal ; et. al. A Graph-Based Approach to Skill Extraction from Text.TextGraphs-8 Graph-based Methods for Natural Language Processing (Seattle, USA, du 18/10/2013 au 19/10/2013).
Permanent URL http://hdl.handle.net/2078.1/136968