Neural Networks for Multi-Word Expression Detection - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Neural Networks for Multi-Word Expression Detection

Natalia Klyueva
  • Fonction : Auteur
  • PersonId : 1082995
Milan Straka
  • Fonction : Auteur
  • PersonId : 1082996

Résumé

In this paper we describe the MUMULS system that participated to the 2017 shared task on automatic identification of verbal multiword expressions (VMWEs). The MUMULS system was implemented using a supervised approach based on recurrent neural networks using the open source library TensorFlow. The model was trained on a data set containing annotated VMWEs as well as morphological and syntactic information. The MU-MULS system performed the identification of VMWEs in 15 languages, it was one of few systems that could categorize VMWEs type in nearly all languages.
Fichier principal
Vignette du fichier
W17-1707.pdf (107.29 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03025446 , version 1 (26-11-2020)

Identifiants

Citer

Natalia Klyueva, Antoine Doucet, Milan Straka. Neural Networks for Multi-Word Expression Detection. Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017), Apr 2017, Valencia, Spain. pp.60-65, ⟨10.18653/v1/W17-1707⟩. ⟨hal-03025446⟩

Collections

L3I UNIV-ROCHELLE
105 Consultations
206 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More