Tuning Statistical Machine Translation Parameters

Abstract: Word alignment is the basis of statistical machine
translation. GIZA++ is a popular tool for producing word alignments
and translation models. It uses a set of parameters that affect the
quality of word alignments and translation models. These parameters
exist to overcome some problems such as overfitting. This paper
addresses the problem of tuning GIZA++ parameter for better
translation quality. The results show that our systematic procedure
for parameter tuning can improve the translation quality.
Publication year 2004
Pages 15-18
Organization Name
Country Turkey
Publisher Name: ENFORMATIKA
serial title International Journal of Information Technology
Web Page
ISSN 1305-2403
Volume VOLUME 1 .
Author(s) from ARC
Agris Categories Documentation and information
Proposed Agrovoc Parameter tuning; smoothing factors; training;
Publication Type Journal