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.
Publication year 2005
Organization Name
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