The resources in the KIM default IE pipeline depend on the KIM default ontology - the PROTON ontology. It is the formal structure of the KIM knowledge base. PROTON is a generic upper-level ontology, which consists of about 100 classes and 300 properties of general worldly notions. If you want to use the full functionality of KIM, when using a new ontology, the best is to map it to PROTON.
Due to the complexity of the IE process, adding a new ontology to KIM and making KIM aware of it, is not a one step process. If the PROTON ontology and the new one are very similar as a domain, you only have to align them, which means mapping the terms that are used for the same notions. But if they are completely different, then you have to go through all the stages of integrating an ontology in KIM. In most cases, the task is a mixture of both. Part of the new ontology may be usable by just aligning it to PROTON, and the other part - by making the processing resources aware of this new part (adding it to lists, creating new grammar rules etc.).
For additional information about how to extend the KIM Information Extraction capabilities, please see the respective section in the KIM administrator's guide:
http://www.ontotext.com/kim/getting-started/documentation
Labels:
None