Training phrase-based SMT without explicit word aligment

Cyrine Nasri 1 Kamel Smaïli 1 Chiraz Latiri 2
1 SMarT - Statistical Machine Translation and Speech Modelization and Text
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
2 URPAH Tunis
URPAH - Unité de Recherche en Programmation Algorithmique et Heuristique
Abstract : The machine translation systems usually build an initial word-to-word alignment, before training the phrase translation pairs. This approach requires a lot of matching between different single words of both considered languages. In this paper, we propose a new approach for phrase-based machine translation which does not require any word alignment. This method is based on inter-lingual triggers retrieved by Multivariate Mutual Information. This algorithm segments sentences into phrases and fnds their alignments simultaneously. The main objective of this work is to build directly valid alignments between source and target phrases. The achieved results, in terms of performance are satisfactory and the obtained translation table is smaller than the reference one; this approach could be considered as an alternative to the classical methods.
Keywords : Statistical Machine Translation Inter-Lingual triggers Multivariate Mutual Information
Type de document :
Communication dans un congrès
15th International Conference on Intelligent Text Processing and Computational Linguistics, Apr 2014, Kathmandu, Nepal. Springer, Lecture Notes in Computer Science, 8404, pp.233-241, 2014, Computational Linguistics and Intelligent Text Processing. 〈https://link.springer.com/chapter/10.1007/978-3-642-54903-8_20〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/hal-01067051
Contributeur : Kamel Smaïli <>
Soumis le : lundi 22 septembre 2014 - 18:06:40
Dernière modification le : mardi 24 avril 2018 - 13:30:46

Fichier

CICLING2014Nasri.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01067051, version 1

Collections

UNIV-LORRAINE | LORIA | LORIA-NLPKD | INRIA

Citation

Cyrine Nasri, Kamel Smaïli, Chiraz Latiri. Training phrase-based SMT without explicit word aligment. 15th International Conference on Intelligent Text Processing and Computational Linguistics, Apr 2014, Kathmandu, Nepal. Springer, Lecture Notes in Computer Science, 8404, pp.233-241, 2014, Computational Linguistics and Intelligent Text Processing. 〈https://link.springer.com/chapter/10.1007/978-3-642-54903-8_20〉. 〈hal-01067051〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

216

Téléchargements de fichiers

7

Contact


archive-ouverte@inria.fr