GAWO: Genetic-based optimization algorithm for SMT - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2017

GAWO: Genetic-based optimization algorithm for SMT

Abstract

In this work, we propose GAWO, a new method for SMT parameters optimization based on the genetic algorithms. Like other existing methods, GAWO performs the optimization task through two nested loops, one for the translation and the other for the optimization. However, our proposition is especially designed to optimize the feature weights of the fitness function of GAMaT, a new genetic-based decoder for SMT. We tested GAWO to optimize GAMaT for French-English and Turkish-English translation tasks, and the results showed that we out-perform the previous performance by +4.0 points according to the BLEU for French-English and by +2.2 points for Turkish-English.
Fichier principal
Vignette du fichier
ICNLSSP2017_paper_18.pdf (225.48 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01660010 , version 1 (09-12-2017)

Identifiers

  • HAL Id : hal-01660010 , version 1

Cite

Ameur Douib, David Langlois, Kamel Smaili. GAWO: Genetic-based optimization algorithm for SMT. ICNLSSP 2017 - International Conference on Natural Language, Signal and Speech Processing, ISGA, Dec 2017, Maroc, Morocco. ⟨hal-01660010⟩
624 View
178 Download

Share

Gmail Facebook X LinkedIn More