A Translation Evaluation Function based on Neural Network - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Schedae Informaticae Année : 2017

A Translation Evaluation Function based on Neural Network

Résumé

In this paper, we study the feasibility of using a neural network to learn a fitness function for a machine translation system based on a genetic algorithm termed GAMaT. The neural network is learned on features extracted from pairs of source sentences and their translations. The fitness function is trained in order to estimate the BLEU of a translation as precisely as possible. The estimator has been trained on a corpus of more than 1.3 million data. The performance is very promising: the difference between the real BLEU and the one given by the estimator is equal to 0.12 in terms of Mean Absolute Error.
Fichier principal
Vignette du fichier
Article_tfml2017_FinalVersion.pdf (302.45 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01531584 , version 1 (01-06-2017)

Identifiants

Citer

Ameur Douib, David Langlois, Kamel Smaili. A Translation Evaluation Function based on Neural Network. Schedae Informaticae, 2017, 25, pp.139-151. ⟨10.4467/20838476SI.16.011.6192⟩. ⟨hal-01531584⟩
232 Consultations
109 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More