Sciweavers

170 search results - page 3 / 34
» Online Large-Margin Training for Statistical Machine Transla...
Sort
View
EMNLP
2008
13 years 6 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 6 months ago
A Systematic Comparison of Training Criteria for Statistical Machine Translation
We address the problem of training the free parameters of a statistical machine translation system. We show significant improvements over a state-of-the-art minimum error rate tr...
Richard Zens, Sasa Hasan, Hermann Ney
COLING
2008
13 years 6 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
CICLING
2008
Springer
13 years 7 months ago
Dynamic Translation Memory: Using Statistical Machine Translation to Improve Translation Memory Fuzzy Matches
Abstract. Professional translators of technical documents often use Translation Memory (TM) systems in order to capitalize on the repetitions frequently observed in these documents...
Ergun Biçici, Marc Dymetman
ACL
2008
13 years 6 months ago
Name Translation in Statistical Machine Translation - Learning When to Transliterate
We present a method to transliterate names in the framework of end-to-end statistical machine translation. The system is trained to learn when to transliterate. For Arabic to Engl...
Ulf Hermjakob, Kevin Knight, Hal Daumé III