Dr. D. PIEK VOSSEN

The KYOTO project: an implementation of the Global Wordnet Grid

In this presentation, I will describe the KYOTO project, which is funded by the European Union and by national funds in Taiwan and Japan. The goal of KYOTO is a system that allows people in communities to define the meaning of their words and terms in a shared Wiki platform so that they become anchored across languages and cultures but also so that a computer can use this knowledge to detect knowledge and facts in text. The languages of the project are English, Dutch, Italian, Spanish, Basque, Chinese and Japanese and the domain is the environment. However, the system can be extended for any other language and to any other domain. Whereas the current Wikipedia uses free text to share knowledge, KYOTO will represent this knowledge so that a computer can understand it. For example, the notion of environmental footprint may become defined in the same way in all these languages but also in such a way that the computer knows what information is necessary to calculate a footprint. With these definitions it will be possible to find information on footprints in documents, websites and reports so that users can directly ask the computer for actual information in their environment, e.g. what is the footprint of their town, their region, their company or their personal footprint.
The terms for a community are automatically acquired from the documents in the domains but can be edited and modified by the domain experts in the Wiki. The edited terms are represented as a domain wordnet that is linked to generic wordnets in the languages. Similarly, a domain ontology is created that is linked to a generic ontology. The editing is supported through text from which the terms are derived and complex knowledge structures are hidden for the user. The KYOTO platform is thus not developed for knowledge engineers but for Semantic Web2.0 communities that maintain their own knowledge and wordnets, creating Semantic Web3.0 structures and services. By linking domain wordnets to generic wordnets and to a shared ontology, the KYOTO project can become the backbone for developing the Global Wordnet Grid. When the domain modeling is done, the acquired knowledge can be used for open text mining. Users can specify a conceptual profile that is mapped to the text in the domain through expression rules and wordnets to find fact in the text. The facts are aggregated from the text and presented in an RDF repository for search. The conceptual knowledge in the community is thus directly applied for interpretation of the factual knowledge in the community.