arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1603.04402cs.AI
收藏

超大规模常识知识库中的搜索控制:一种机器学习方法

Controlling Search in Very large Commonsense Knowledge Bases: A Machine Learning Approach

Cycorp, Inc.(Cycorp公司);Lucid AI(Lucid AI公司)

Abhishek Sharma, Michael Witbrock, Keith Goolsbey

摘要:

非常大的常识知识库(KBs)通常有数千到数百万个公理,其中相对较少的公理与回答任何给定的查询相关。大量不相关的公理很容易淹没基于解析的定理证明器。因此,帮助推理机识别有用的推理路径的方法形成了大规模推理系统的重要组成部分。在本文中,我们描述了两个排序算法优化的推理在这样的系统。首先,我们讨论如何使用决策树来选择更有可能成功的推理步骤。其次,我们确定了一个小的问题实例功能,足以引导搜索远离棘手的区域的搜索空间。我们通过实验从Cyc KB的数千个查询,这些技术的有效性。结果表明,这些方法导致一个数量级的减少推理时间。

英文摘要:

Very large commonsense knowledge bases (KBs) often have thousands to millions of axioms, of which relatively few are relevant for answering any given query. A large number of irrelevant axioms can easily overwhelm resolution-based theorem provers. Therefore, methods that help the reasoner identify useful inference paths form an essential part of large-scale reasoning systems. In this paper, we describe two ordering heuristics for optimization of reasoning in such systems. First, we discuss how decision trees can be used to select inference steps that are more likely to succeed. Second, we identify a small set of problem instance features that suffice to guide searches away from intractable regions of the search space. We show the efficacy of these techniques via experiments on thousands of queries from the Cyc KB. Results show that these methods lead to an order of magnitude reduction in inference time.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑