When a knowledge repository gets very large, finding a particular piece of knowledge can become very difficult. There are two related problems to
do with knowledge retrieval. First, there is the issue of finding knowledge again once it has been stored, understanding the structure of your
archive in order to navigate through it efficiently. And second, there is the problem of retrieving the subset of content from the repository that
is relevant to a particular problem. This second problem, the dynamic extraction of knowledge from a repository, may well set problems for a
knowledge retrieval system that alter regularly and quickly during problem-solving.
In knowledge retrieval, the aim would be to develop user-friendly tools for retrieving knowledge from repositories. One obvious place to begin is
to try to exploit natural language. Natural language can be used as the basis for the interface to our knowledge services. For instance, ontologies
could be used to interpret knowledge queries in natural language forms from users.
The other focus of our effort to meet this challenge is focused around the technologies behind the interface. Our expertise in a number of areas,
such as search engines, multimedia thesauri, capability decisions and statistical sampling will be used to increase the efficiency of retrieval
technologies, and to provide technologies that cope with the new demands of the semantic web.
In particular, we are very alive to the technological possibilities of the enriched markup of web pages. Given the central importance of the
Internet, web pages will clearly be a vital storage and dissemination medium for knowledge. The use of semantic markup technologies such as XML or
RDF, driven by our proven knowledge technologies such as ontologies and dynamic hypertext link generation, will enable efficient and accurate
retrieval of web pages from the web itself, or from highly structured and possibly very complex intranets.
When knowledge is stored or retrieved, it is important to remove any duplication to avoid overloading users with knowledge. AKT is developing a
variety of knowledge fusion techniques to identify and remove such duplications before presenting knowledge to the user.
AKT Technologies addressing issues in Knowledge Retrieval --
A core C library that uses MySQL to store its raw RDF data and caches,
forming an important part of the infrastructure required to support a
range of knowledgeable services.
An open, lightweight, Web standards-based communication infrastructure to support interoperability among knowledge services.
- ANNIE - Open Source Information Extraction
An open-source robust information extraction system
AQUA is a system which answer questions written in English. It combines several technologies
Natural Language Processing, Logic, Information Retrieval and Ontologies.
A system that automatically extracts information about artists from the web, populates an ontology, then uses the knowledge to generate personalised biographies.
- CS AKTiveSpace
CS AKTiveSpace is a smart browser interface for a Semantic Web application that provides ontologically motivated information about the UK computer science research community.
Compendium is a semantic, visual hypertext tool for supporting
collaborative domain modelling and real time meeting capture
A programmable XML editor which is being used in a
knowledge extraction role to transform Web pages into
ExtrAKT is a tool for extracting ontologies from Prolog knowledge bases.
A prototype system which demonstrates the benefits of applying
semantically rich service descriptions (expressed using Semantic
Web technologies) to Web Services.
Foxtrot is a recommender system which represents user profiles in ontological terms, allowing inference, bootstrapping and profile visualization.
- GATE - General Architecture for Text Engineering
GATE is a stable, robust, and scalable open-source infrastructure
which allows users to build and customise language processing
components, while it handles mundane tasks like data storage, format
analysis and data visualisation.
- Knowledge Broker
The knowledge broker addresses the problem of knowledge service
location in distributed environments.
Magpie supports the interpretation of web documents through
on-the-fly ontologically based enrichment. Semantic services can be
invoked either by the user or be automatically triggered by patterns
of browsing activity
MyPlanet allows users to create a personalised version of a web based
newsletter using an ontologically based profile.
A tool which uncovers Communities Of Practise by analysing the connectivity of instances in the 3store knowledge base.