We propose a novel language-independent approach for improving statistical machine translation for resource-poor languages by exploiting their similarity to resource-rich ones. Mo...
Many description logics (DLs) combine knowledge tation on an abstract, logical level with an interface to “concrete” domains such as numbers and strings. We propose to extend ...
Carsten Lutz, Carlos Areces, Ian Horrocks, Ulrike ...
The paper argues, that a direct formalization of the way common sense thinks about the numerical identity of enduring entities, requires that traditional predicate logic is develo...
The genetic programming (GP) paradigm is a new approach to inductively forming programs that describe a particular problem. The use of natural selection based on a fitness ]unction...
In this paper, we introduce a method that automatically builds text classifiers in a new language by training on already labeled data in another language. Our method transfers the...