This paper describes two aspects of architecture of componentized systems. First, properties of the basic building blocks (acquisition and presentation components) are discussed a...
We present a concept to use off-line learning approaches to achieve on-line learning of cooperative behavior of agents and instantiate this concept for evolutionary learning with ...
There is a signi cant di erence between documentinglarge programs and documenting small ones. By large programs we mean on the order of 1,000,000 lines, usually written by many di...
DBMT is researched here in the context of future systems for the general public, where a monolingual author wants to translate into several languages. We have produced a complete ...
Tense and aspect, together with mood and modality, usually form the entangled structure of a complex verb. They are often hard to translate by machines, because of both syntactic ...