Exploring a Continuous and Flexible Representation of the Lexicon - Équipe de Recherche : Textes, Informatique, Multilinguisme Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Exploring a Continuous and Flexible Representation of the Lexicon

Résumé

We aim at showing that lexical descriptions based on multifactorial and continuous models can be used by linguists and lexicographers (and not only by machines) so long as they are provided with a way to efficiently navigate data collections. It is widely accepted that word description cannot be achieved without the analysis of a large number of contexts extracted from real corpora. The recent success of deep learning approaches has shown that discrete representations of the lexicon are no longer appropriate. Continuous models offer a better representation of word meaning, because they encode intuitively valid and cognitively plausible principles: semantic similarity is relative, context-sensitive and depends on multiple-cue integration. We propose tod demonstrate such a system that is usable both by machines and by humans.
Fichier principal
Vignette du fichier
C16-2062.pdf (319.38 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-01422479 , version 1 (26-12-2016)

Identifiants

  • HAL Id : hal-01422479 , version 1

Citer

Pierre Marchal, Thierry Poibeau. Exploring a Continuous and Flexible Representation of the Lexicon. 26th International Conference on Computational Linguistics (COLING 2016), Dec 2016, Osaka, Japan. pp.297-301. ⟨hal-01422479⟩
294 Consultations
104 Téléchargements

Partager

Gmail Facebook X LinkedIn More