arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.04070cs.CL
收藏

所有好的词向量空间都是同构的吗?

Are All Good Word Vector Spaces Isomorphic?

University of Cambridge(剑桥大学);DeepMind(深度思维);University of Copenhagen(哥本哈根大学);Google Research(谷歌研究院)

Ivan Vulić, Sebastian Ruder, Anders Søgaard

摘要:

现有的跨语言词向量空间对齐算法假设向量空间是近似同构的。因此,它们在非同构空间上表现不佳或完全失败。这种非同构现象被认为是语言类型差异的结果。在这项工作中,我们问是否非同构也是至关重要的退化词向量空间的一个标志。我们提出了一系列的实验,在不同的语言表明,跨语言对的性能的差异不仅是由于类型的差异,但可以主要归因于可用的单语资源的大小,以及单语训练的属性和持续时间(例如“训练不足”)。

英文摘要:

Existing algorithms for aligning cross-lingual word vector spaces assume that vector spaces are approximately isomorphic. As a result, they perform poorly or fail completely on non-isomorphic spaces. Such non-isomorphism has been hypothesised to result from typological differences between languages. In this work, we ask whether non-isomorphism is also crucially a sign of degenerate word vector spaces. We present a series of experiments across diverse languages which show that variance in performance across language pairs is not only due to typological differences, but can mostly be attributed to the size of the monolingual resources available, and to the properties and duration of monolingual training (e.g. "under-training").

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。

↑