We describe a new approach to SMT adaptation that weights out-of-domain phrase pairs according to their relevance to the target domain, determined by both how similar to it they a...
This paper aims to provide an experimental vision of the process of course creation using learning objects obtained in the <e-aula> project, a pilot e-learning system concei...
The reward functions that drive reinforcement learning systems are generally derived directly from the descriptions of the problems that the systems are being used to solve. In so...
This paper investigates adapting a lexicalized probabilistic context-free grammar (PCFG) to a novel domain, using maximum a posteriori (MAP) estimation. The MAP framework is gener...
This paper presents a theoretical analysis of the problem of domain adaptation with multiple sources. For each source domain, the distribution over the input points as well as a h...