Sciweavers

2391 search results - page 122 / 479
» From Nature to Methods and Back to Nature
Sort
View
EMNLP
2009
14 years 7 months ago
Unsupervised Tokenization for Machine Translation
Training a statistical machine translation starts with tokenizing a parallel corpus. Some languages such as Chinese do not incorporate spacing in their writing system, which creat...
Tagyoung Chung, Daniel Gildea
EMNLP
2009
14 years 7 months ago
Model Adaptation via Model Interpolation and Boosting for Web Search Ranking
This paper explores two classes of model adaptation methods for Web search ranking: Model Interpolation and error-driven learning approaches based on a boosting algorithm. The res...
Jianfeng Gao, Qiang Wu, Chris Burges, Krysta Marie...
EMNLP
2009
14 years 7 months ago
Effective Use of Linguistic and Contextual Information for Statistical Machine Translation
Current methods of using lexical features in machine translation have difficulty in scaling up to realistic MT tasks due to a prohibitively large number of parameters involved. In...
Libin Shen, Jinxi Xu, Bing Zhang, Spyros Matsoukas...
ICIP
2009
IEEE
15 years 11 months ago
Image Restoration By Mixture Modelling Of An Overcomplete Linear Representation
We present a new image restoration method based on modelling the coefficients of an overcomplete wavelet response to natural images with a mixture of two Gaussian distributions, h...
ICDM
2009
IEEE
125views Data Mining» more  ICDM 2009»
15 years 4 months ago
A Fully Automated Method for Discovering Community Structures in High Dimensional Data
—Identifying modules, or natural communities, in large complex networks is fundamental in many fields, including social sciences, biological sciences and engineering. Recently s...
Jianhua Ruan