Linguistic information extraction for job ads (SIRE project)

Romain Loth (1) , Delphine Battistelli (2) , François-Régis Chaumartin (3) , Hugues de Mazancourt (4) , Jean-Luc Minel (1) , Axelle Vinckx (4)

1 MoDyCo - Modèles, Dynamiques, Corpus
2 STIH - Sens, Texte, Informatique, Histoire
3 Proxem
4 Lingway Labs

As a text, each job advertisement expresses rich information about the occupation at hand, such as competence needs (i.e. required degrees, field knowledge, task expertise or technical skills). To facilitate the access to this information, the SIRE project conducted a corpus based study of how to articulate HR expert ontologies with modern semi-supervised information extraction techniques. An adaptive semantic labeling framework is developed through a parallel work on retrieval rules and on latent semantic lexicons of terms and jargon phrases. In its operational stage, our prototype will collect online job ads and index their content into detailed RDF triples compatible with applications ranging from enhanced job search to automated labor-market analysis.

Mots clés: Information storage and retrieval; Content Analysis and Indexing; abstracting methods; dictionaries; indexing methods; linguistic processing

Domaines: Linguistique; Informatique

Romain Loth, Delphine Battistelli, François-Régis Chaumartin, Hugues de Mazancourt, Jean-Luc Minel, et al.. Linguistic information extraction for job ads (SIRE project). 9th international conference on Adaptivity, Personalization and Fusion of Heterogeneous Information, Apr 2010, Paris, France. pp.300-303. ⟨halshs-00480840⟩