Shift-map image processing is a new framework based on energy minimization over a large space of labels. The optimization utilizes α-expansion moves and iterative refinement ove...
One reason why Case-Based Reasoning (CBR) has become popular is because it reduces development cost compared to rule-based expert systems. Still, the knowledge engineering effort ...
The lack of large-scale, freely available and durable lexical resources, and the consequences for NLP, is widely acknowledged but the attempts to cope with usual bottlenecks preven...
Franck Sajous, Emmanuel Navarro, Bruno Gaume, Laur...
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...
Tagging systems have become major infrastructures on the Web. They allow users to create tags that annotate and categorize content and share them with other users, very helpful in...