Valuable knowledge has been distributed in heterogeneous formats on many different Web sites and other sources over the Internet. However, finding the needed information is a complex task since there is a lack of semantic relations and organization between them. This chapter presents a problem-solving map framework for extracting and integrating knowledge from unstructured documents on the Internet by exploiting the semantic links between problems, methods for solving them and the people who could solve them. This challenging area of research needs both complex natural language processing, including deep semantic relation interpretation, and the participation of end-users for annotating the answers scattered on the Web. The framework is evaluated by generating problem solving maps for rice and human diseases.
The lessons learned from solving past problems (e.g. how to protect oneself from a disease, how to control the plant disease) and gaining valuable information from previous experience (e.g. disease diagnosis) and the history of disease recurrences (e.g. disease outbreaks) are invaluable for guaranteeing food safety and human health. To reduce the time that users take to learn from such information, a salient information space with semantic link should be developed.
Problem-solving is an intelligent behavior (Kennedy J., et al., 2001) where the goal is to find a solution which satisfies certain criteria. It requires abductive reasoning whereby we apply deductive reasoning in combination with natural language processing. In classical applications as well as in expert systems, abductive inference (Shohei K., et al., 2003) is a complex problem (creation and maintenance) as it is simulated by deductive procedures or rules. On the other hand, qualitative reasoning concerns modeling and inference techniques where continuous phenomena are discretized into a finite number of qualitative categories. In this chapter, language engineering is described as a tool for extracting knowledge represented in unstructured format. The extracted knowledge will be a finite number of specific answers to queries on topics “cause-and-effect “such as disease and symptoms., “problem-and -how-to-do” such disease prevention or control, and biomedicine preparation.