Genetic-based Decoder for Statistical Machine Translation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Book Sections Year : 2016

Genetic-based Decoder for Statistical Machine Translation

Abstract

We propose a new algorithm for decoding on machine translation process. This approach is based on an evolutionary algorithm. We hope that this new method will constitute an alternative to Moses's decoder which is based on a beam search algorithm while the one we propose is based on the optimisation of a total solution. The results achieved are very encouraging in terms of measures and the proposed translations themselves are well built.
Fichier principal
Vignette du fichier
VersionFinalePapierCICLing16-Ameur.pdf (378.05 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01336546 , version 1 (23-06-2016)

Identifiers

  • HAL Id : hal-01336546 , version 1

Cite

Ameur Douib, David Langlois, Kamel Smaili. Genetic-based Decoder for Statistical Machine Translation. Springer LNCS series, Lecture Notes in Computer Science, 2016. ⟨hal-01336546⟩
221 View
278 Download

Share

Gmail Facebook X LinkedIn More