Moving QA Towards Reading Comprehension Using Context and Default Reasoning

Christine Clark, Daniel Hodges, Jens Stephan, and Dan Moldovan

For a question answering system to understand the underlying assumptions and contextual features of natural language, a contextually and semantically sensitive knowledge representation and reasoning module is essential. This paper proposes a three-layered knowledge representation coupled with reasoning mechanisms for defaults and contexts as a solution for pushing question answering towards a state capable of basic reading comprehension. A travel scenario is presented as a vehicle for demonstrating the complexities of this problem, and the ways in which semantic relations, contexts (for conditionality, planning, time, and space), and defaults address these complexities.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.