75 search results - page 7 / 15 » Minimum Bayes-Risk Decoding for Statistical Machine Translat... |
COLING
2008
13 years 9 months ago
2008
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...
ACL
2003
13 years 9 months ago
2003
Often, the training procedure for statistical machine translation models is based on maximum likelihood or related criteria. A general problem of this approach is that there is on...
TASLP
2008
13 years 7 months ago
2008
This paper presents a novel online relevant set algorithm for a linearly-scored block sequence translation model. The key component is a new procedure to directly optimize the glob...
EMNLP
2010
13 years 6 months ago
2010
Extant Statistical Machine Translation (SMT) systems are very complex softwares, which embed multiple layers of heuristics and embark very large numbers of numerical parameters. A...
ACL
2007
13 years 9 months ago
2007
Inspired by previous preprocessing approaches to SMT, this paper proposes a novel, probabilistic approach to reordering which combines the merits of syntax and phrase-based SMT. G...