Sciweavers

59 search results - page 3 / 12
» Diversify and Combine: Improving Word Alignment for Machine ...
Sort
View
FINTAL
2006
13 years 9 months ago
Improving Phrase-Based Statistical Translation Through Combination of Word Alignments
This paper investigates the combination of word-alignments computed with the competitive linking algorithm and well-established IBM models. New training methods for phrase-based st...
Boxing Chen, Marcello Federico
AMTA
2004
Springer
13 years 10 months ago
Multi-align: Combining Linguistic and Statistical Techniques to Improve Alignments for Adaptable MT
Abstract. An adaptable statistical or hybrid MT system relies heavily on the quality of word-level alignments of real-world data. Statistical alignment approaches provide a reasona...
Necip Fazil Ayan, Bonnie J. Dorr, Nizar Habash
ACL
2008
13 years 6 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...
ACL
2012
11 years 7 months ago
Deciphering Foreign Language by Combining Language Models and Context Vectors
In this paper we show how to train statistical machine translation systems on reallife tasks using only non-parallel monolingual data from two languages. We present a modificatio...
Malte Nuhn, Arne Mauser, Hermann Ney
EMNLP
2009
13 years 3 months ago
Weighted Alignment Matrices for Statistical Machine Translation
Current statistical machine translation systems usually extract rules from bilingual corpora annotated with 1-best alignments. They are prone to learn noisy rules due to alignment...
Yang Liu, Tian Xia, Xinyan Xiao, Qun Liu