The AIDA Toolkit is directed at groups of knowledge workers that cooperatively search, annotate, interpret, and enrich large collections of heterogeneous documents from diverse locations. It is a generic set of components that can perform a variety of tasks such as learn new pattern recognition models, perform specialized search on resource collections, and store knowledge in a repository. W3C standards are used to make data accessible and manageable with semantic web technologies such as OWL, RDF(S), and SKOS. AIDA is also based on Lucene and Sesame. Most components are available as web services and open source.
Our server offers services for:
- text indexing
- text statistics
- metadata storage and querying
- thesaurus reasoning
- annotation
- text retrieval
- spelling correction
- synonym detection
- model learning
Several applications are being built from AIDA on several platforms, including Taverna workflows, a web-based AIDA search and annotation tool, a VBrowser plugin, and a Taverna plugin. We are also working on use cases in several domains such as for food informatics, rule maintenance for clinical decision support, knowledgebase maintenance, and knowledge discovery and knowledge capture in biology.
Some movies which show the AIDA search interface in action can be found here. A movie of the Taverna plugin in action can be found here.
AIDA Toolkit is Apache 2.0 licensed code. If you agree to Apache 2.0 licensing terms, you can DOWNLOAD HERE (>100MB).
Note: AIDA stands for “Adaptive Information Disclosure Application”