arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.01873cs.AIcs.CL
收藏

嵌入空间中的概念泛化

Towards conceptual generalization in the embedding space

Kagi.ai Research(Kagi.ai研究院)

Luka Nenadović, Vladimir Prelovac

摘要:

人类能够通过共同学习物理实相的不同方面来构思物理实相。每一对与感知的实在相关的概念都可能对应一种相互关系,这种相互关系本身就是一种概念,但更高一个层次。因此,我们可以在至少两个层面上对感知现实进行描述,并且由于它们的不同内容语料库,它们之间的翻译映射通常是一对多的。在无监督神经机器翻译模型(本质上是在单语语料库上单独训练的一对一映射)成功之后,我们进一步研究了其中使用的无监督深度学习方法的功能,并将其中一些方法应用于不同级别和度量的概念集。利用图和类似词嵌入的技术,我们建立了一对多的映射,没有并行数据,以建立一个统一的矢量表示的外部世界,通过结合不同种类的概念到一个独特的概念框架。由于它们的潜在相似性,通过以纯粹无监督的方式对齐两个嵌入空间,人们可以在两个层面上获得认知对象之间的几何关系,从而可以在另一个的上下文中使用一个描述来表达自然知识。

英文摘要:

Humans are able to conceive physical reality by jointly learning different facets thereof. To every pair of notions related to a perceived reality may correspond a mutual relation, which is a notion on its own, but one-level higher. Thus, we may have a description of perceived reality on at least two levels and the translation map between them is in general, due to their different content corpus, one-to-many. Following success of the unsupervised neural machine translation models, which are essentially one-to-one mappings trained separately on monolingual corpora, we examine further capabilities of the unsupervised deep learning methods used there and apply some of these methods to sets of notions of different level and measure. Using the graph and word embedding-like techniques, we build one-to-many map without parallel data in order to establish a unified vector representation of the outer world by combining notions of different kind into a unique conceptual framework. Due to their latent similarity, by aligning the two embedding spaces in purely unsupervised way, one obtains a geometric relation between objects of cognition on the two levels, making it possible to express a natural knowledge using one description in the context of the other.

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。

↑