Sciweavers

146 search results - page 6 / 30
» Analysis and System Combination of Phrase- and N-Gram-Based ...
Sort
View
EMNLP
2008
13 years 9 months ago
Lattice-based Minimum Error Rate Training for Statistical Machine Translation
Minimum Error Rate Training (MERT) is an effective means to estimate the feature function weights of a linear model such that an automated evaluation criterion for measuring syste...
Wolfgang Macherey, Franz Josef Och, Ignacio Thayer...
JMLR
2011
187views more  JMLR 2011»
13 years 2 months ago
Exploitation of Machine Learning Techniques in Modelling Phrase Movements for Machine Translation
We propose a distance phrase reordering model (DPR) for statistical machine translation (SMT), where the aim is to learn the grammatical rules and context dependent changes using ...
Yizhao Ni, Craig Saunders, Sándor Szedm&aac...
ECAI
2008
Springer
13 years 9 months ago
Improved Statistical Machine Translation Using Monolingual Paraphrases
We propose a novel monolingual sentence paraphrasing method for augmenting the training data for statistical machine translation systems "for free"
Preslav Nakov
LREC
2010
176views Education» more  LREC 2010»
13 years 9 months ago
Integrating a Rule-based with a Hierarchical Translation System
Recent developments on hybrid systems that combine rule-based machine translation (RBMT) systems with statistical machine translation (SMT) generally neglect the fact that RBMT sy...
Yu Chen, Andreas Eisele
IBPRIA
2003
Springer
14 years 29 days ago
Combining Phrase-Based and Template-Based Alignment Models in Statistical Translation
In statistical machine translation, single-word based models have an important deficiency; they do not take contextual information into account for the translation decision. A poss...
Jesús Tomás, Francisco Casacuberta