The objective of this paper is to study the existing methods for unsupervised object recognition and image categorization and propose a model that can learn directly from the outp...
We study the problem of anonymizing user profiles so that user privacy is sufficiently protected while the anonymized profiles are still effective in enabling personalized web sea...
Untranslated words still constitute a major problem for Statistical Machine Translation (SMT), and current SMT systems are limited by the quantity of parallel training texts. Augm...
Correctly generating a structured query (e.g., an XQuery or a SQL query) requires the user to have a full understanding of the database schema, which can be a daunting task. Alter...
The Web of Linked Data grows rapidly and already contains data originating from hundreds of data sources. The quality of data from those sources is very diverse, as values may be ...