PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Explicit Length Modelling for Statistical Machine Translation
Joan Albert Silvestre-Cerda, Jesús Andrés-Ferrer and Jorge Civera
In: IbPRIA 2011(2011).

Abstract

Explicit length modelling has been previously explored in statistical pattern recognition with successful results. In this paper, two length models along with two parameter estimation methods for statis- tical machine translation (SMT) are presented. More precisely, we in- corporate explicit length modelling in a state-of-the-art log-linear SMT system as an additional feature function in order to prove the contribu- tion of length information. Finally, promising experimental results are reported on a reference SMT task.

EPrint Type:Conference or Workshop Item (Talk)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Natural Language Processing
ID Code:8796
Deposited By:Alfons Juan
Deposited On:21 February 2012