Usually, human-computer dialogue systems rely on ad-hoc solutions for the component performing speech turn generation, in natural language. However, integration of taskspecific and general world knowledge in order to provide a more reliable and natural interaction with humans also through more sophisticated language generation techniques becomes needed. In this paper we present performance impr...

Discourse models have received significant attention in the computational linguistics community with some important connections to the non-computational discourse community. More recently, the importance of discourse annotation has increased as models generated with supervised machine learning techniques are being used to annotate text automatically. A primary area for annotation is science. Th...

In order to build robust automatic abstracting systems, there is a need for better training resources than are currently available. In this paper, we introduce an annotation scheme for scientific articles which can be used to build such a resource in a consistent way. The seven categories of the scheme are based on rhetorical moves of argumentation. Our experimental results show that the scheme...

The role of enteroviruses in certain specific disease--cardiac disease, nephritis, diabetes, and hemorrhagic conjunctivitis--is examined. It has now been well documented that Coxsackievirus B (types CB1 through CB5 but not CB6) is the main pathogen involved in various clinical forms of viral heart disease. Coxsackievirus A (CA4 and CA16) and echovirus (types 9 and 22) may also be associated wit...

Natural zeolites occur in over 40 countries and are mined in 11 of these at a rate of around 250 thousand tonnes per year. Discovery of the characteristic ion-exchange, dehydration and selective-adsorption properties of these zeolites, which are related to their unique honeycomb structure, stimulated the development of severa1 processes for the manufacture of synthetic zeolites. These synthetic...

In this article, we propose a novel method for generating engaging multi-modal content automatically from text. Rhetorical Structure Theory (RST) is used to decompose text into discourse units and to identify rhetorical discourse relations between them. Rhetorical relations are then mapped to question–answer pairs in an information preserving way, i.e., the original text and the resulting dialo...