466 search results - page 26 / 94 » Large Language Models in Machine Translation |
EMNLP
2008
15 years 1 months ago
2008
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimi...
105
click to vote
ACL
2012
13 years 2 months ago
2012
Long distance word reordering is a major challenge in statistical machine translation research. Previous work has shown using source syntactic trees is an effective way to tackle ...
114
click to vote
CSL
2004
Springer
14 years 11 months ago
2004
Springer
We propose new methods to exploit contemporaneous text, such as on-line news articles, to improve language models for automatic speech recognition and other natural language proce...
100
click to vote
LREC
2008
15 years 1 months ago
2008
In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model ...
NLPRS
2001
Springer
15 years 4 months ago
2001
Springer
In this paper, we present CaptionEye/KE, a Korean to English machine translation system that is applied to a practical TV caption translation. And its experimental evaluation is p...