Sciweavers

373 search results - page 53 / 75
» Trainable Methods for Surface Natural Language Generation
Sort
View
CAE
2010
14 years 4 months ago
Learning about Shadows from Artists
Renaissance artists discovered methods for imaging realistic depth on a two dimensional surface by re-inventing linear perspective. In solving the problem of depth depiction, they...
Elodie Fourquet
IJCNLP
2005
Springer
15 years 3 months ago
Automatic Image Annotation Using Maximum Entropy Model
Automatic image annotation is a newly developed and promising technique to provide semantic image retrieval via text descriptions. It concerns a process of automatically labeling t...
Wei Li, Maosong Sun
COLING
2010
14 years 4 months ago
Discriminative Training for Near-Synonym Substitution
Near-synonyms are useful knowledge resources for many natural language applications such as query expansion for information retrieval (IR) and paraphrasing for text generation. Ho...
Liang-Chih Yu, Hsiu-Min Shih, Yu-Ling Lai, Jui-Fen...
RE
2005
Springer
15 years 3 months ago
Using Occurrence Properties of Defect Report Data to Improve Requirements
Defect reports generated for faults found during testing provide a rich source of information regarding problematic phrases used in requirements documents. These reports indicate ...
Kimberly S. Wasson, Kendra N. Schmid, Robyn R. Lut...
ICCD
2003
IEEE
127views Hardware» more  ICCD 2003»
15 years 6 months ago
Structural Detection of Symmetries in Boolean Functions
Functional symmetries provide significant benefits for multiple tasks in synthesis and verification. Many applications require the manual specification of symmetries using spe...
Guoqiang Wang, Andreas Kuehlmann, Alberto L. Sangi...