Traditional methods for implementing highly resilient systems are costly; and their methods using specialized hardware and high-speed interconnects do not extend to cloud. We demonstrate an architecture that rethinks the traditional approach and uses cloud's agility to provision additional capability as failures occur. This architecture continues serving requests with the best possible response even as the primary service deteriorates and even fails completely. It offloads requests according to their need to access the primary service; first redirecting requests with less need to lower-grade secondary capability that is provisioned on-demand on the cloud in order to reserve primary capacity for requests that need it (e.g., first redirect web-browsing requests to a slightly out-of-date cached dataset, and reserve the primary, most-consistent data service for check-out requests). Our approach 1) triages access to the primary service based on request needs in times when it is overwhelmed, and 2) provisions on-demand cloud capability to offload and continue serving other requests as needed. The result is a highly resilient system architecture that scales via cloud.

We describe a problem solver built to answer questions like those on advanced placement exams using knowledge bases authored by domain experts. The problem solver is designed to work independently of any particular knowledge base or domain. Given a question, the problem solver identifies those portions of the knowledge base that are relevant to the question. We found that simple heuristics for judging relevance significantly improved performance, with no drop in coverage.

As part of the ongoing project, Project Halo, our goal is to build a system capable of answering questions posed by novice users to a formal knowledge base. In our current context, the knowledge base covers selected topics in physics, chemistry, and biology, and our question set consists of AP (advanced high-school) level examination questions. The task is challenging because the questions are linguistically complex and are often incomplete (assume unstated knowledge), and because the users do not have prior knowledge of the system's contents. Our solution involves two parts: a controlled language interface, in which users reformulate the original natural language questions in a simplified version of English, and a novel problem solver that can elaborate initially inadequate logical interpretations of a question by selecting relevant pieces of knowledge in the knowledge base. An evaluation of the work in 2006 showed that this approach is feasible and that complex, multisentence questions can be posed and answered, thus illustrating novel ways of dealing with the knowledge capture impedance between users and a formal knowledge base, while also revealing challenges that still remain.

An important problem in artificial intelligence is capturing, from natural language, formal representationsallthat can be used by a reasoner to compute an answer. Many researchers have studied this problem by developing algorithms addressing specific phenomena in natural language interpretation, but few have studied (or cataloged) the types of failures associated with this problem. Knowledgeallof these failures can help researchers by providing a roadallmap of open research problems and help practitioners by providing a checklist of issues to address in order to build systems that can achieve good performance on this problem.allIn this paper, we present a study -- conducted in the context of the Halo Project -- cataloging the types of failures that occur when capturing knowledge from naturallanguage. We identified the categories of failures by examining a corpus of questions posed byallnaive usersallto a knowledge based question answering system and empirically demonstrated the generality of ourallcategorizations. We also describe available technologies that can address some of the failures we have identified.