Sciweavers

737 search results - page 9 / 148
» Network Structuring and Training Using Rule-Based Knowledge
Sort
View
EACL
1989
ACL Anthology
14 years 10 months ago
It Would Be Much Easier If WENT Were GOED
The paper proposes a paradigmatic approach to morphological knowledge acquisition. It addresses the problem of learning from examples rules for word-forms analysis and synthesis. ...
Dan Tufis
KDD
2008
ACM
183views Data Mining» more  KDD 2008»
15 years 10 months ago
Knowledge transfer via multiple model local structure mapping
The effectiveness of knowledge transfer using classification algorithms depends on the difference between the distribution that generates the training examples and the one from wh...
Jing Gao, Wei Fan, Jing Jiang, Jiawei Han
EACL
2006
ACL Anthology
14 years 11 months ago
Using Encyclopedic Knowledge for Named entity Disambiguation
We present a new method for detecting and disambiguating named entities in open domain text. A disambiguation SVM kernel is trained to exploit the high coverage and rich structure...
Razvan C. Bunescu, Marius Pasca
ICA
2010
Springer
14 years 10 months ago
Use of Prior Knowledge in a Non-Gaussian Method for Learning Linear Structural Equation Models
Abstract. We discuss causal structure learning based on linear structural equation models. Conventional learning methods most often assume Gaussianity and create many indistinguish...
Takanori Inazumi, Shohei Shimizu, Takashi Washio
IJCNN
2006
IEEE
15 years 3 months ago
Training Reformulated Product Units in Hybrid Neural Networks
— Higher order networks allow modelling of correlates and geometrically invariant properties. Current techniques for their development either require domain knowledge, or are con...
Philip T. Elliott, Diven Topiwala, Will N. Browne