Abstract We consider the task of data-to-text generation, which aims to create textual output from non-linguistic input. focus on generating long-form text, that is, documents with multiple paragraphs, and propose a neural model enhanced planning component responsible for organizing high-level information in coherent meaningful way. infer latent plans sequentially structured variational model, ...

The generation business in the U.S. is currently undergoing a transition from a regulated monopoly toward an uncertain, competitive market. Under the competitive market, the price of electric power as well as the corresponding revenue may be much less certain than before. These market uncertainties have increased the significance of two critical factors in generation planning. These factors are...

The subject of the paper is planning of distribution network in case of integration of distributed generation on weak medium voltage network. Because network long-term planning includes major uncertainties and integration of distributed generation has remarkable effects at these areas, final network plans may be done after the integration agreement has been concluded. In order to limit the pric...

In this paper we use formal argumentation theory to study the deliberation cycle of the BOID cognitive agent architecture. We combine goal generation with a planning approach recently proposed by Leila Amgoud. In her formal argumentation framework plans for fulfilling a desire are represented just like arguments that support a conclusion; the framework can thus deal with conflicting desires. In...