Ontology And Its Application In The Intercultural Collaboration Environment

The prevalence of Internet promotes the collaboration and communication amoun users all over the world. However, the collaboration between the users of Asian countries is limited because of high language barrier. It's an imminent task to strengthen the communication in Asia. lntercultural Collaboration Environment (ICE) which is sponsored by Prof. Toru Ishida at Kyoto University is a joint research project of universities, research institutes, and research societies in Asia. The objective of ICE is to support intercultural and multilingual collaborations using machine translation technologies (MT).Although the translation tools such as TransBBS, AnnoChat are able to translate messages among Chinese, English, Japanese, and Korean, the quality is a little weak and the users can't understand each other very well.To improve the mutual understanding of users using their native languages in Asia, an ontology-based ICE framework was proposed in which ontology, agent and data mining techniques were integrated. With the support of this framework, the translation results of AnnoChat are easier to be understood. The work of this theis is focused on the ontology module.Ontology is a formal specification of a shared conceptualization. It provides means for describing explicitly the conceptualization behind the knowledge represent-ed in a knowledge base and it's helpful to disambiguate polyseme. As a result, we established an ontology named Domain Ontology to provide semantic support for the Ontology-Based ICE System. In addition, in order to adapt to dynamics and changes in the operating environment, we introduce a user-oriented four-phase evolution model for Domain Ontology, which can obtain the ontology version according to the user's preference.The experimental results show that the Ontology-Based ICE System disambigu-ates polyseme more effectively compared with AnnoChat. While, the prototype system DOES implemented according to the proposed four-phase ontology evolution model evolves Domain Ontology effectively.