Sciweavers

616 search results - page 84 / 124
» Statistical Phrase-Based Translation
Sort
View
ACL
2008
15 years 3 months ago
Exploiting N-best Hypotheses for SMT Self-Enhancement
Word and n-gram posterior probabilities estimated on N-best hypotheses have been used to improve the performance of statistical machine translation (SMT) in a rescoring framework....
Boxing Chen, Min Zhang, AiTi Aw, Haizhou Li
IMAGING
2003
15 years 3 months ago
Color and Color Constancy in a Translation Model for Object Recognition
Color is of interest to those working in computer vision largely because it is assumed to be helpful for recognition. This assumption has driven much work in color based image ind...
Kobus Barnard, Prasad Gabbur
ACL
2009
14 years 11 months ago
Quadratic-Time Dependency Parsing for Machine Translation
Efficiency is a prime concern in syntactic MT decoding, yet significant developments in statistical parsing with respect to asymptotic efficiency haven't yet been explored in...
Michel Galley, Christopher D. Manning
IPM
2011
71views more  IPM 2011»
14 years 5 months ago
Improving semistatic compression via phrase-based modeling
In recent years, new semistatic word-based byte-oriented text compressors, such as Tagged Huffman and those based on Dense Codes, have shown that it is possible to perform fast d...
Nieves R. Brisaboa, Antonio Fariña, Gonzalo...
SIGIR
1998
ACM
15 years 6 months ago
Resolving Ambiguity for Cross-Language Retrieval
Abstract One of the main hurdles to improved CLIR effectiveness is resolving ambiguity associated with translation. Availability of resources is also a problem. First we present a ...
Lisa Ballesteros, W. Bruce Croft