Knowledge integration across multiple texts

One of the grand challenges of AI is to build systems that learn by reading. The ideal system would construct a rich knowledge base capable of automated reasoning. We have built a Learning-by-Reading system and this paper focuses on one aspect of it: the task of integrating together snippets of knowledge drawn from multiple texts to build a single coherent knowledge base. Our evaluation shows that our approach to the knowledge integration is both feasible and promising. Categories and Subject Descriptors I.2.6 [Artificial Intelligence]: Learning—Knowledge Acquisition; I.2.7 [Artificial Intelligence]: Natural Language Processing—Discourse General Terms Algorithms Keywords knowledge acquisition, knowledge integration, natural language understanding, learning-by-reading

• Type: Conference
• Year: 2009
• Where: KCAP
• Authors: Doo Soon Kim, Ken Barker, Bruce W. Porter
• Keywords: Information Retrieval, KCAP 2009, Knowledge Base, Knowledge Integration, Rich Knowledge Base