STATISTICAL MACHINE TRANSLATION IMPROVEMENT BASED ON PHRASE SELECTION

Cyrine Nasri 1, 2 Latiri Chiraz 1, 2 Kamel Smaili 2
2 SMarT - Statistical Machine Translation and Speech Modelization and Text
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : This paper describes the importance of introducing a phrase-based language model in the process of machine translation. In fact, nowadays SMT are based on phrases for translation but their language models are based on classical ngrams. In this paper we introduce a phrase-based language model (PBLM) in the decoding process to try to match the phrases of a translation table with those predicted by a language model. Furthermore, we propose a new way to retrieve phrases and their corresponding translation by using the principle of conditional mutual information. The SMT developed will be compared to the baseline one in terms of BLEU, TER and METEOR. The experimental results show that the introduction of PBLM in the translation decoding improve the results.
Type de document :
Communication dans un congrès
Recent Advances in Natural Language Processing, Sep 2015, Hissar, Bulgaria
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01261563
Contributeur : Kamel Smaïli <>
Soumis le : mardi 26 janvier 2016 - 11:43:24
Dernière modification le : mardi 24 avril 2018 - 13:35:12
Document(s) archivé(s) le : mercredi 27 avril 2016 - 13:18:30

Fichier

ranlp2015PhraseSelection.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01261563, version 1

Collections

Citation

Cyrine Nasri, Latiri Chiraz, Kamel Smaili. STATISTICAL MACHINE TRANSLATION IMPROVEMENT BASED ON PHRASE SELECTION. Recent Advances in Natural Language Processing, Sep 2015, Hissar, Bulgaria. 〈hal-01261563〉

Partager

Métriques

Consultations de la notice

194

Téléchargements de fichiers

56