عربى
Claes Home Page
Objectives
Achievement
Organizational Structure
CLAES Projects
Expert Systems
online Expert Systems
Publications
Reasearch Staff
Worshops
Collaborating Institutions
intrnal Links
 
Titles
English : Tuning Statistical Machine Translation Parameters Using Perplexity
Abstract Statistical Machine Translation (SMT) involves many tasks including modeling, training, decoding, and evaluation. In this work, we present a methodology for optimizing the training process to get better translation quality using the well known GIZA++ SMT toolkit. The methodology is based on adjusting the parameters of GIZA++ that affect the generation of the translation model. When applying the methodology, an average improvement of 7% has been achieved in the translation quality.
URL
Publication year 2005
Organization Name
    Central Laboratory for Agricultural Expert System (CLAES)
Country United States
City Las Vegas, Nevada, USA
Publisher Name: IEEE
serial title IEEE International Conference on Information Reuse and Integration (IEEE IRI-2005)
Web Page
Author(s) from ARC
Agris Categories Documentation and information
Proposed Agrovoc Statistical Machine Translation; parameter tuning; perplexity;
Publication Type Conference/Workshop

 
Please email your suggestions to management@claes.sci.eg