State-of-the-art NLG systems have a mostly static perspective on language generation, i.e. they have a fixed knowledge representation from which they generate language. This is fine for offline working systems, where the language is read only after it has been completely generated. However, systems set in a dynamic environment, e.g. those interacting with a human user, need a dynamic way of pro...

Ontologging is an ontology-driven environment to enable next generation knowledge management applications building on Semantic Web technology. In this paper we first present the conceptual architecture underlying Ontologging. Second, we focus on two important challenges for ontology-based knowledge management, namely the supporting multiple ontologies and managing ontology evolution. We will pr...

This paper is a contribution towards the exploration of semantic interfaces in text generation systems. It suggests a general interpretation of semantics for the purpose of text generation as an interlevel between lexicogrammar (the resources of grammar and vocabulary) and higher levels of organization (knowledge base, user model, text planning, and so on). Two approaches to the design of this ...

Purpose The purpose of this research is to understand the mechanisms of knowledge management (KM) for innovation and provide an approach for enterprises to leverage KM activities into continuous innovation. Design/methodology/approach – By reviewing the literature from multidisciplinary fields, the concepts of knowledge, KM and innovation are investigated. The physical, human and technological ...

Volatile events such as public health disasters bring the prospect of rapid contagion and the threat of disastrous impacts for Europe. Vulnerabilities and cascading effects can result in significant injuries, illness and loss of life. Damage to health infrastructure, demand for medical attention, displacement and major outbreaks all place a strain on health services. Preparedness, response and ...

Automated text generation requires a underlying knowledge base from which to generate, which is often difficult to produce. Software documentation is one domain in which parts of this knowledge base may be derived automatically. In this paper, we describe drafter, an authoring support tool for generating usercentred software documentation, and in particular, we describe how parts of its require...

This paper presents an implemented model of spoken language processing that accounts for intonational phenomena associated with semantic contrasts. The model determines accentual patterns based on sets of alternative properties from a knowledge base and a contrastive stress algorithm. The results of applying the model to a natural language generation program illustrate the advantages over previ...

We propose an approach to generate natural language questions from knowledge graphs such as DBpedia and YAGO. We stage this in the setting of a quiz game. Our approach, though, is general enough to be applicable in other settings. Given a topic of interest (e.g., Soccer) and a di culty (e.g., hard), our approach selects a query answer, generates a SPARQL query having the answer as its sole resu...

Terminal Time is a machine that constructs ideologicallybiased documentary histories in response to audience feedback. The audience answers multiple-choice questions via an applause meter. The answers to these questions influence which historical events are chosen from a knowledge base, how these events will be slanted to embody the bias implied in the audience's answers, and how the events wil...

We address the problem of improving the reliability of independence-based causal discovery algorithms that results from the execution of statistical independence tests on small data sets, which typically have low reliability. We model the problem as a knowledge base containing a set of independence facts that are related through Pearl’s well-known axioms. Statistical tests on finite data sets m...