Sciweavers

1229 search results - page 61 / 246
» A New Method for Dependent Parsing
Sort
View
EMNLP
2006
13 years 10 months ago
Domain Adaptation with Structural Correspondence Learning
Discriminative learning methods are widely used in natural language processing. These methods work best when their training and test data are drawn from the same distribution. For...
John Blitzer, Ryan T. McDonald, Fernando Pereira
COLING
2002
13 years 8 months ago
Learning Chinese Bracketing Knowledge Based on a Bilingual Language Model
This paper proposes a new method for automatic acquisition of Chinese bracketing knowledge from English-Chinese sentencealigned bilingual corpora. Bilingual sentence pairs are fir...
Yajuan Lü, Sheng Li, Tiejun Zhao, Muyun Yang
BMCBI
2005
114views more  BMCBI 2005»
13 years 8 months ago
A new decoding algorithm for hidden Markov models improves the prediction of the topology of all-beta membrane proteins
Background: Structure prediction of membrane proteins is still a challenging computational problem. Hidden Markov models (HMM) have been successfully applied to the problem of pre...
Piero Fariselli, Pier Luigi Martelli, Rita Casadio
PAKDD
1999
ACM
113views Data Mining» more  PAKDD 1999»
14 years 1 months ago
Characterization of Default Knowledge in Ripple Down Rules Method
Abstract. \Ripple Down Rules (RDR)" Method is one of the promising approaches to directly acquire and encode knowledge from human experts. It requires data to be supplied incr...
Takuya Wada, Tadashi Horiuchi, Hiroshi Motoda, Tak...
GW
2005
Springer
119views Biometrics» more  GW 2005»
14 years 2 months ago
Dynamic Control of Captured Motions to Verify New Constraints
Simulating realistic human-like figures is still a challenging task when dynamics is involved. For example, making a virtual human jump to a given position requires to control the...
Carole Durocher, Franck Multon, Richard Kulpa