The Internet presents numerous sources of useful information--telephone directories, product catalogs, stock quotes, event listings, etc. Recently, many systems have been built th...
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
Automatic generation of semantic metadata describing spatial relations is highly desirable for image digital libraries. Relative spatial relations between objects in an image conv...
Yuhang Wang, Fillia Makedon, James Ford, Li Shen, ...
The problem of automatically extracting the most interesting and relevant keyword phrases in a document has been studied extensively as it is crucial for a number of applications. ...
An adaptive user interface relies, to a large extent, upon an adequate user model (e.g., a representationof user-expertise). However, building a user model may be a tedious and ti...