An Ontology-Driven Multi-Agent Architecture for Knowledge Acquisition from Text in NKI

NKI contains a multi-domain oriented and large scale knowledge base. Text corpus is an important knowledge source of it. This paper presents an ontology-driven and integrated multi-agent architecture (MAKAT) for achieving sharing and reuse among different kinds of knowledge acquisition in NKI. MAKAT is a three-tier model which involves KATO, KARO, KATA, among which the description and execution layer are discussed in detail. Finally, we utilize the MAKAT model to acquire two different relations: part-of relation and hyponymy. It is observed that the MAKAT model can provide sharing and reuse in these two different cases