Using an incremental robust parser to automatically generate semantic UNL graphs - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2004

Using an incremental robust parser to automatically generate semantic UNL graphs

Résumé

The UNL project (Universal Networking Language) proposes a standard for encoding the meaning of natural language utterances as semantic hypergraphs, intended to be used as pivot in multilingual information and communication systems. Several deconverters permit to automatically translate UNL utterances into natural languages. However, a rough enconvertion from natural language texts to UNL expressions is usually done interactively with editors specially designed for the UNL project or by hand (which is very time-consuming and difficult to extrapolate to huge amounts of data). In this paper, we address the issue of using an existing incremental robust parser as main resource to enconverting French utterances into UNL expressions.
Fichier principal
Vignette du fichier
gala-romand_coling04.pdf (116.24 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03198917 , version 1 (15-04-2021)

Identifiants

  • HAL Id : hal-03198917 , version 1

Citer

Núria Gala. Using an incremental robust parser to automatically generate semantic UNL graphs. 3rd Workshop on RObust Methods in Analysis of Natural Language Data (COLING 2004), Aug 2004, Génève, Switzerland. ⟨hal-03198917⟩

Collections

UGA IMAG CNRS
23 Consultations
19 Téléchargements

Partager

Gmail Facebook X LinkedIn More