Explicit length modelling for statistical machine translation

[EN] 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 and two alternative parametrisations for statistical machine translation (SMT) are presented. More prec...

Full description

Bibliographic Details
Authors: Silvestre Cerdà, Joan Albert|||0000-0003-2291-8296, Civera Saiz, Jorge|||0000-0002-0963-0143, Andrés Ferrer, Jesús
Format: article
Publication Date:2012
Country:España
Institution:Universitat Politècnica de València (UPV)
Repository:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Language:English
OAI Identifier:oai:riunet.upv.es:10251/34996
Online Access:https://riunet.upv.es/handle/10251/34996
Access Level:Open access
Keyword:Length modelling
Log-linear models
Phrase-based models
Statistical machine translation
ESTADISTICA E INVESTIGACION OPERATIVA
LENGUAJES Y SISTEMAS INFORMATICOS
Description
Summary:[EN] 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 and two alternative parametrisations for statistical machine translation (SMT) are presented. More precisely, we incorporate explicit bilingual length modelling in a state-of-the-art log-linear SMT system as an additional feature function in order to prove the contribution of length information. Finally, a systematic evaluation on reference SMT tasks considering different language pairs proves the benefits of explicit length modelling.