Abstract:
KLEO is a bootstrapping learning-by-reading system that builds a knowledge base in a fully automated way by reading texts for a domain. KL E O's initial knowledge base is a small knowledge base that consists of domain independent knowledge and KL E O expands the knowledge base with the information extracted from texts. A key facility in KL E O is knowledge integration which combines new information gleaned from individual sentences of the texts, along with prior knowledge, to form a comprehensive and computationally useful knowledge base. This paper introduces the architecture of KL E O, especially the knowledge integration facility, and presents our evaluation plan.