Sciweavers

5647 search results - page 213 / 1130
» A word from the editor
Sort
View
IBPRIA
2003
Springer
15 years 11 months ago
Combining Phrase-Based and Template-Based Alignment Models in Statistical Translation
In statistical machine translation, single-word based models have an important deficiency; they do not take contextual information into account for the translation decision. A poss...
Jesús Tomás, Francisco Casacuberta
COMBINATORICS
2007
64views more  COMBINATORICS 2007»
15 years 6 months ago
An Analogue of the Thue-Morse Sequence
We consider the finite binary words Z(n), n ∈ N, defined by the following selfsimilar process: Z(0) := 0, Z(1) := 01, and Z(n + 1) := Z(n) · Z(n − 1), where the dot · deno...
Emmanuel Ferrand
COLING
2008
15 years 8 months ago
When is Self-Training Effective for Parsing?
Self-training has been shown capable of improving on state-of-the-art parser performance (McClosky et al., 2006) despite the conventional wisdom on the matter and several studies ...
David McClosky, Eugene Charniak, Mark Johnson
CORR
2002
Springer
82views Education» more  CORR 2002»
15 years 6 months ago
Using eigenvectors of the bigram graph to infer morpheme identity
This paper describes the results of some experiments exploring statistical methods to infer syntactic categories from a raw corpus in an unsupervised fashion. It shares certain po...
Mikhail Belkin, John A. Goldsmith
PR
2000
129views more  PR 2000»
15 years 6 months ago
Personal identification based on handwriting
In this paper, a novel algorithm is presented for writer identification from handwritings. Principal Component Analysis is applied to the gray-scale handwriting images to find a s...
H. E. S. Said, T. N. Tan, Keith D. Baker