Inducing Multilingual Text Analysis Tools Using Bidirectional Recurrent Neural Networks

Abstract : This work focuses on the rapid development of linguistic annotation tools for resource-poor languages. We experiment several cross-lingual annotation projection methods using Recurrent Neural Networks (RNN) models. The distinctive feature of our approach is that our multilingual word representation requires only a parallel corpus between the source and target language. More precisely, our method has the following characteristics: (a) it does not use word alignment information, (b) it does not assume any knowledge about foreign languages, which makes it applicable to a wide range of resource-poor languages, (c) it provides truly multilingual taggers. We investigate both uni-and bi-directional RNN models and propose a method to include external information (for instance low level information from POS) in the RNN to train higher level taggers (for instance, super sense taggers). We demonstrate the validity and genericity of our model by using parallel corpora (obtained by manual or automatic translation). Our experiments are conducted to induce cross-lingual POS and super sense taggers.
Type de document :
Communication dans un congrès
COLING 2016, Dec 2016, Osaka, Japan. 2016, 〈http://coling2016.anlp.jp〉
Liste complète des métadonnées

Littérature citée [48 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01374205
Contributeur : Laurent Besacier <>
Soumis le : vendredi 30 septembre 2016 - 07:31:26
Dernière modification le : jeudi 11 octobre 2018 - 08:48:03
Document(s) archivé(s) le : samedi 31 décembre 2016 - 13:01:00

Fichier

coling-2016-3.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01374205, version 1
  • ARXIV : 1609.09382

Citation

Othman Zennaki, Nasredine Semmar, Laurent Besacier. Inducing Multilingual Text Analysis Tools Using Bidirectional Recurrent Neural Networks. COLING 2016, Dec 2016, Osaka, Japan. 2016, 〈http://coling2016.anlp.jp〉. 〈hal-01374205〉

Partager

Métriques

Consultations de la notice

336

Téléchargements de fichiers

108