Sciweavers

240 search results - page 45 / 48
» Translation Model Pruning via Usage Statistics for Statistic...
Sort
View
EMNLP
2007
13 years 9 months ago
Phrase Reordering Model Integrating Syntactic Knowledge for SMT
Reordering model is important for the statistical machine translation (SMT). Current phrase-based SMT technologies are good at capturing local reordering but not global reordering...
Dongdong Zhang, Mu Li, Chi-Ho Li, Ming Zhou
EMNLP
2008
13 years 9 months ago
Improved Sentence Alignment on Parallel Web Pages Using a Stochastic Tree Alignment Model
Parallel web pages are important source of training data for statistical machine translation. In this paper, we present a new approach to sentence alignment on parallel web pages....
Lei Shi, Ming Zhou
BMCBI
2004
91views more  BMCBI 2004»
13 years 7 months ago
SIGI: score-based identification of genomic islands
Background: Genomic islands can be observed in many microbial genomes. These stretches of DNA have a conspicuous composition with regard to sequence or encoded functions. Genomic ...
Rainer Merkl
TASLP
2008
201views more  TASLP 2008»
13 years 7 months ago
Syntactically Lexicalized Phrase-Based SMT
Abstract--Until quite recently, extending Phrase-based Statistical Machine Translation (PBSMT) with syntactic knowledge caused system performance to deteriorate. The most recent su...
Hany Hassan, Khalil Sima'an, Andy Way
CIVR
2004
Springer
117views Image Analysis» more  CIVR 2004»
14 years 1 months ago
Using Maximum Entropy for Automatic Image Annotation
In this paper, we propose the use of the Maximum Entropy approach for the task of automatic image annotation. Given labeled training data, Maximum Entropy is a statistical techniqu...
Jiwoon Jeon, R. Manmatha