Sciweavers

546 search results - page 45 / 110
» Improved Word-Level System Combination for Machine Translati...
Sort
View
ACL
2009
14 years 7 months ago
Joint Decoding with Multiple Translation Models
Current SMT systems usually decode with single translation models and cannot benefit from the strengths of other models in decoding phase. We instead propose joint decoding, a met...
Yang Liu, Haitao Mi, Yang Feng, Qun Liu
ACL
2008
14 years 11 months ago
Better Alignments = Better Translations?
Automatic word alignment is a key step in training statistical machine translation systems. Despite much recent work on word alignment methods, alignment accuracy increases often ...
Kuzman Ganchev, João Graça, Ben Task...
CLEF
2006
Springer
14 years 11 months ago
Experiments for the Cross Language Speech Retrieval Task at CLEF 2006
This paper presents the second participation of the University of Ottawa group in the Cross-Language Speech Retrieval (CL-SR) task at CLEF 2006. We present the results of the submi...
Muath Alzghool, Diana Zaiu Inkpen
EMNLP
2010
14 years 7 months ago
Combining Unsupervised and Supervised Alignments for MT: An Empirical Study
Word alignment plays a central role in statistical MT (SMT) since almost all SMT systems extract translation rules from word aligned parallel training data. While most SMT systems...
Jinxi Xu, Antti-Veikko I. Rosti
EMNLP
2008
14 years 11 months ago
Online Large-Margin Training of Syntactic and Structural Translation Features
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimi...
David Chiang, Yuval Marton, Philip Resnik