arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.01276cs.AI
收藏

学习相关概念的概念空间表示

Learning Conceptual Space Representations of Interrelated Concepts

CRIL CNRS & Univ Artois(CRIL 法国国家科学研究中心与法国亚眠大学);Cardiff University(卡迪夫大学)

Zied Bouraoui, Steven Schockaert

摘要:

最近提出的几种方法旨在从大型文本集合中学习概念空间表示。这些习得的表征将来自给定感兴趣域的每个对象与高维欧几里得空间中的点相关联,但它们不对来自该域的概念进行建模,因此不能直接用于分类和相关的认知任务。一个自然的解决方案是将概念表示为高斯,从其实例的表示中学习,但这只有在给定足够多的实例时才能可靠地做到,而情况往往并非如此。在本文中,我们介绍了一个贝叶斯模型,它解决了这个问题,通过构建信息先验的背景知识的概念是如何相互关联的利益。我们表明,这导致更好的预测,在知识库完成任务。

英文摘要:

Several recently proposed methods aim to learn conceptual space representations from large text collections. These learned representations asso- ciate each object from a given domain of interest with a point in a high-dimensional Euclidean space, but they do not model the concepts from this do- main, and can thus not directly be used for catego- rization and related cognitive tasks. A natural solu- tion is to represent concepts as Gaussians, learned from the representations of their instances, but this can only be reliably done if sufficiently many in- stances are given, which is often not the case. In this paper, we introduce a Bayesian model which addresses this problem by constructing informative priors from background knowledge about how the concepts of interest are interrelated with each other. We show that this leads to substantially better pre- dictions in a knowledge base completion task.

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。

↑