Browsing by Subject "Question answering"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Addressing the brittleness of knowledge-based question-answering(2009-12) Chaw, Shaw Yi; Porter, Bruce, 1956-; Barker, Kenneth J.; Mooney, Raymond; Novak, Gordon S.; Markman, ArtKnowledge base systems are brittle when the users of the knowledge base are unfamiliar with its content and structure. Querying a knowledge base requires users to state their questions in precise and complete formal representations that relate the facts in the question with relevant terms and relations in the underlying knowledge base. This requirement places a heavy burden on the users to become deeply familiar with the contents of the knowledge base and prevents novice users to effectively using the knowledge base for problem solving. As a result, the utility of knowledge base systems is often restricted to the developers themselves. The goal of this work is to help users, who may possess little domain expertise, to use unfamiliar knowledge bases for problem solving. Our thesis is that the difficulty in using unfamiliar knowledge bases can be addressed by an approach that funnels natural questions, expressed in English, into formal representations appropriate for automated reasoning. The approach uses a simplified English controlled language, a domain-neutral ontology, a set of mechanisms to handle a handful of well known question types, and a software component, called the Question Mediator, to identify relevant information in the knowledge base for problem solving. With our approach, a knowledge base user can use a variety of unfamiliar knowledge bases by posing their questions with simplified English to retrieve relevant information in the knowledge base for problem solving. We studied the thesis in the context of a system called ASKME. We evaluated ASKME on the task of answering exam questions for college level biology, chemistry, and physics. The evaluation consists of successive experiments to test if ASKME can help novice users employ unfamiliar knowledge bases for problem solving. The initial experiment measures ASKME's level of performance under ideal conditions, where the knowledge base is built and used by the same knowledge engineers. Subsequent experiments measure ASKME's level of performance under increasingly realistic conditions. In the final experiment, we measure ASKME's level of performance under conditions where the knowledge base is independently built by subject matter experts and the users of the knowledge base are a group of novices who are unfamiliar with the knowledge base. Results from the evaluation show that ASKME works well on different knowledge bases and answers a broad range of questions that were posed by novice users in a variety of domains.Item Answering questions about dynamic domains from natural language using ASP(2011-08) Todorova, Yana; Gelfond, Michael; Watson, Richard; Zhang, YuanlinAnswer Set Programming (ASP) is a knowledge representation methodology that has well-established theoretical foundations and good practical uses. The goal of my dissertation was to build an automatic system for answering non-trivial questions from texts in natural language. This is an important task, because the results are very useful in many areas. The final result of this work is an elaboration tolerant question answering system MQA capable of giving provably correct answers. We also used this research to test our reasoning techniques, such as reasoning in dynamic domains, where movement is involved, and reasoning about changes in cardinalities. The original discourse was written in our controlled language MCL , which allowed us to remove a variety of natural language phenomena and to focus on limited grammar rules and on a restricted vocabulary. For the actual reasoning, we used ASP, because of its nonmonotonic features, and its ability to represent defaults and dynamic domains. Thus, given a discourse and a question in our controlled natural language MCL, we first generated a new logic form representation. We represented the knowledge using action language ALM and we included background information not found in the original text. After that, we performed commonsense reasoning using ASP axioms. Finally, we obtained the correct and expected answer to the question.