Exploring the Utility of ResearchCyc for Reasoning from Natural Language

摘要

This project investigated the potential for using ResearchCyc in natural language processing systems. The project focused particularly on natural language problems connected to sentence understanding, such as reading comprehension and robust textual inference. The project completed studies of the possibilities for using ResearchCyc knowledge for problems from this domain, it developed software for interaction between robust natural language processing systems and ResearchCyc, via its Java interface, and evaluated in a quantitative manner how much value could be gained from use of ResearchCyc and other alternative technologies by performing ablation studies.