CEM-DIT

CEM-DIT is about getting information about the state of a disaster to people who have to make decisions on disaster response, in a way that allows them to understand and trust that information.

The aim of the project is: To provide and automated system to support decision makers during emergency responses by providing item with the information they need in a timely and usable fashion.

This a complex problem and there are lots of angles to consider. CEM-DIT is particularly interested in the following two questions:

1) How do we create a common picture from a large number of data sources that use different terminology, structure, organisation and formats?

2) How can decision makers be sure of the quality and reliability of the information that they receive?

The first problem is addressed through dynamic data integration and matching using the CHAIn system and the second through provenance using the ProvABS system.

The hypothesis of the project is: It is possible tointegrate matching technology with provenance-aware securityin order to allow fast, effective querying of mismatched data sources, and to annotate the response such that thequerier is able to understand its quality and meaning.

The CEM-DIT project is funded by ONR and is a collaboration between Heriot-Watt University, the University of Newcastle and the University of Coventry.

ESSENCE

ESSENCE is a European research training network that conducts world-leading research into the evolution and negotiation of meaning among human and artificial agents.

Since late 2013, it has supported the work of 15 early-career researchers, the ESSENCE Fellows,  on topics that investigate semantic technologies, language games, multiagent communication, ontology learning, and human dialogue, and which all contribute to a broader research vision of diversity-aware AI. This vision emphasises creating next-generation AI technologies that can be used to bridge the gap between heterogeneous agents by exploring how representation, reasoning, and interaction can be used to allow diverse collectives of agents to share information and knowledge, coordinate their activities, and combine their individual capabilities.

ESSENCE aims to build a community around this vision and to promote diversity-awareness as an important challenge for AI. To this end, the network runs a host of events, provides open datasets and software that allow other researchers to engage with our work, and has developed a challenge competition to allow broader communities to engage with the challenges we are interested in.

ESSENCE is funded by the EU and involves 11 partners across Europe.

CHAIn

The CHAIn (Combining Heterogenous Agencies Information) system is designed to dynamically rewrite queries when they fail because of heterogeneities in the data between the agency making the query and the agency receiving the query.  Such failures are almost inevitable unless the sending agency already has a thorough understanding of the receiver’s data: using CHAIn allows successful queries to be made even when the data source is unknown.

Work on CHAIn has been funded by ONR, EPSRC and Dstl.  Researchers on the project include:

Fiona McNeill (lead), Diana Bental (current), Tanya Howden (current), Gábor Bella (previous), Andriana Gkaniatsou (previous).

GAELIC WORDNET

We are currently working to develop a Gaelic wordnet, thesaurus and dictionary.  This will be a useful resource for people as well as automated systems.

The project is funded by EPSRC and involves Heriot-Watt University, the University of the Highlands and Islands and the University of Trento.