Calculation of phrase probabilities for Statistical Machine Translation by using belief functions - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Calculation of phrase probabilities for Statistical Machine Translation by using belief functions

Résumé

In this paper, we consider a specific part of statistical machine translation: feature estimation for the translation model. The classical way to estimate these features is based on relative frequencies. In this new approach, we propose to use the concept of belief masses to estimate the phrase translation probabilities. The Belief Function theory has proven to be suitable and adapted for dealing with uncertainties in many domains. We have performed a series of experiments to translate from English into French and from Arabic into English showing that our approach performs, at least as well as and at times better than, the classical approach.
Fichier principal
Vignette du fichier
C12-2107.pdf (111.72 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01158098 , version 1 (29-05-2015)

Identifiants

  • HAL Id : hal-01158098 , version 1

Citer

Christophe Servan, Simon Petitrenaud. Calculation of phrase probabilities for Statistical Machine Translation by using belief functions. The 24th International Conference on Computational Linguistics (COLING 2012), Dec 2012, Mumbai, India. ⟨hal-01158098⟩
122 Consultations
57 Téléchargements

Partager

Gmail Facebook X LinkedIn More