Learning to Perform Knowlege Intensive Inferences

本研究的目的是研究学习、知识表示和推理的集成理论，并在自然语言领域的大规模知识密集型推理中对其进行评估。最近在“学习推理”框架内的研究表明，在一个统一的框架内研究这些问题会有很多收获。本研究调查了这个框架内的一些基本问题——集中在概率设置上。重点是开发算法，利用该领域中一些“传统”假设的松弛。这包括对学习算法的要求（例如，学习一个“好的”密度估计），推理算法（例如，统一地支持*所有*查询）以及在这个领域中研究的一些知识表示。对这些理论在自然语言领域的应用进行了实验研究和评价。重点是结合低级学习算法来执行高级推理的学习方法和表示。这项研究将对理解一些涉及学习和推理结合的基本问题产生影响，并将允许在弥合自然语言领域低级工作和高级目标之间的差距方面取得具体进展。http://L2R.cs.uiuc.edu/ danr /授予/ nsf98.ht毫升

The goal of this research is to study an integrated theory of learning, knowledge representation and reasoning and evaluate it on large scale knowledge intensive inferences in the natural language domain. Recent studies, within the Learning to Reason framework, have shown that there is much to gain from studying these issues within a unified framework. This research investigates some of the fundamental issues within this framework -- concentrating on a probabilistic setting. The emphasis is on developing algorithms that exploit the relaxation of some of the ``traditional'' assumptions in this domain. These include requirements put on the learning algorithms (e.g., learn a ``good'' density estimation), reasoning algorithms (e.g., support *all* queries uniformly well) and on some of the knowledge representations studied in this domain. Application of these theories to the natural language domain are studied and evaluated experimentally. The emphasis is on learning methods and representations for combining lowlevel learning algorithms to perform higher level inferences. This research will have impact both on understanding some of the fundamental issues involved in combining learning and reasoning and will allow for making concrete progress towards bridging the gap between the low-level work and higher level goals in the natural language domain. http://L2R.cs.uiuc.edu/~danr/Grants/nsf98.ht ml