39 search results - page 5 / 8 » Tuning statistical machine translation parameters using perp... |
JMLR
2008
13 years 7 months ago
2008
This paper investigates statistical performances of Support Vector Machines (SVM) and considers the problem of adaptation to the margin parameter and to complexity. In particular ...
LREC
2010
13 years 9 months ago
2010
Statistical machine translation (SMT) requires a large parallel corpus, which is available only for restricted language pairs and domains. To expand the language pairs and domains...
EMNLP
2010
13 years 5 months ago
2010
Minimum Error Rate Training is the algorithm for log-linear model parameter training most used in state-of-the-art Statistical Machine Translation systems. In its original formula...
ACL
2012
11 years 10 months ago
2012
We propose a simple generative, syntactic language model that conditions on overlapping windows of tree context (or treelets) in the same way that n-gram language models condition...
ICML
2005
IEEE
14 years 8 months ago
2005
IEEE
We present a directed Markov random field (MRF) model that combines n-gram models, probabilistic context free grammars (PCFGs) and probabilistic latent semantic analysis (PLSA) fo...