Personalization of help system output in the framework of everyday language computing

This paper discusses providing the personalized output of a help system when a user has difficulties in operating computer software. The knowledge for personalization is stored in a client model, which is one of the modules in a client secretary in the framework of Everyday Language Computing. Three functions of the client model, i.e., paraphrasing, supplementing and omission, and inference, are performed to modify the existing help text so that it will be easily understood to users. Focusing on user's knowledge, we have constructed a user's knowledge level judging system. Finally, the importance of the personalization of the help output is discussed with an example dialogue.