Sciweavers

803 search results - page 10 / 161
» Cognates Can Improve Statistical Translation Models
Sort
View
COLING
2008
13 years 10 months ago
Improving Statistical Machine Translation using Lexicalized Rule Selection
This paper proposes a novel lexicalized approach for rule selection for syntax-based statistical machine translation (SMT). We build maximum entropy (MaxEnt) models which combine ...
Zhongjun He, Qun Liu, Shouxun Lin
LREC
2008
138views Education» more  LREC 2008»
13 years 10 months ago
MISTRAL: a Statistical Machine Translation Decoder for Speech Recognition Lattices
This paper presents MISTRAL, an open source statistical machine translation decoder dedicated to spoken language translation. While typical machine translation systems take a writ...
Alexandre Patry, Philippe Langlais
EMNLP
2008
13 years 10 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...
EMNLP
2007
13 years 10 months ago
What Can Syntax-Based MT Learn from Phrase-Based MT?
We compare and contrast the strengths and weaknesses of a syntax-based machine translation model with a phrase-based machine translation model on several levels. We briefly descr...
Steve DeNeefe, Kevin Knight, Wei Wang 0006, Daniel...
COLING
2008
13 years 10 months ago
A Systematic Comparison of Phrase-Based, Hierarchical and Syntax-Augmented Statistical MT
Probabilistic synchronous context-free grammar (PSCFG) translation models define weighted transduction rules that represent translation and reordering operations via nonterminal s...
Andreas Zollmann, Ashish Venugopal, Franz Josef Oc...