Explicit length modelling for statistical machine translation

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...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition 2012-09, Vol.45 (9), p.3183-3192
Main Authors: Silvestre-Cerdà, Joan Albert, Andrés-Ferrer, Jesús, Civera, Jorge
Format: Article
Language:English
Subjects:
Applied sciences
Detection, estimation, filtering, equalization, prediction
Exact sciences and technology
Information, signal and communications theory
Length modelling
Log-linear models
Machine translation
Mathematical models
Miscellaneous
Modelling
Parameter estimation
Pattern recognition
Phrase-based models
Signal and communications theory
Signal processing
Signal, noise
State of the art
Statistical machine translation
Tasks
Telecommunications and information theory
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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. ► Development of novel phrase-length models in statistical machine translation (SMT). ► Proposal of parameter estimation methods and parametrisations for these models. ► Analysis and discussion of the performance of phrase-length models. ► Systematic comparison of estimation methods and parametrisations across languages. ► Automatic evaluation on reference tasks proved the benefits of length modelling.
ISSN:0031-3203
1873-5142
DOI:10.1016/j.patcog.2012.01.006