NOMIT: Automatic Titling by Nominalizing - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

NOMIT: Automatic Titling by Nominalizing

Résumé

The important mass of textual documents is in perpetual growth and requires strong applications to automatically process information. Automatic titling is an essential task for several applications: 'No Subject' e-mails titling, text generation, summarization, and so forth. This study presents an original approach consisting in titling journalistic articles by nominalizing. In particular, morphological and semantic processing are employed to obtain a nominalized form which has to respect titles characteristics (in particular, relevance and catchiness). The evaluation of the approach, described in the paper, indicates that titles stemming from this method are informative and/or catchy.
Fichier principal
Vignette du fichier
naaclhlt2012.pdf (141.28 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

lirmm-00706647 , version 1 (11-06-2012)

Identifiants

  • HAL Id : lirmm-00706647 , version 1

Citer

Cédric Lopez, Violaine Prince, Mathieu Roche. NOMIT: Automatic Titling by Nominalizing. NAACL'2012: North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun 2012, Montréal, Canada. pp.274-283. ⟨lirmm-00706647⟩
162 Consultations
292 Téléchargements

Partager

Gmail Facebook X LinkedIn More