Sciweavers

563 search results - page 18 / 113
» Following directions using statistical machine translation
Sort
View
EMNLP
2010
13 years 5 months ago
Discriminative Instance Weighting for Domain Adaptation in Statistical Machine Translation
We describe a new approach to SMT adaptation that weights out-of-domain phrase pairs according to their relevance to the target domain, determined by both how similar to it they a...
George F. Foster, Cyril Goutte, Roland Kuhn
EMNLP
2009
13 years 5 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
COLING
2010
13 years 2 months ago
Translation Model Generalization using Probability Averaging for Machine Translation
Previous methods on improving translation quality by employing multiple SMT models usually carry out as a secondpass decision procedure on hypotheses from multiple systems using e...
Nan Duan, Hong Sun, Ming Zhou
COLING
2008
13 years 9 months ago
Random Restarts in Minimum Error Rate Training for Statistical Machine Translation
Och's (2003) minimum error rate training (MERT) procedure is the most commonly used method for training feature weights in statistical machine translation (SMT) models. The u...
Robert C. Moore, Chris Quirk
EMNLP
2006
13 years 9 months ago
Phrasetable Smoothing for Statistical Machine Translation
We discuss different strategies for smoothing the phrasetable in Statistical MT, and give results over a range of translation settings. We show that any type of smoothing is a bet...
George F. Foster, Roland Kuhn, Howard Johnson