Visual Exploration of Word Vector Embeddings
Visual Exploration of Word Vector Embeddings
复制标题
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Florian Heimerl;Michael Gleicher
中科院分区：
文献类型：
--
作者：
Florian Heimerl;Michael Gleicher
词向量嵌入作为文本处理中许多上游任务的基础，大大提高了准确性。然而，这种成功的确切原因在很大程度上仍然不清楚，因为这些嵌入编码的属性和关系通常不太清楚。在这个正在进行的项目中，我们的目标是设计有效的交互式可视化，帮助从业者和研究人员更好地理解和比较这些空间。我们采取的第一步是回顾相关文献，以确定对各种应用很重要的词向量的属性和关系。从这些，我们得出的基本任务，通知设计充分和有效的交互式可视化，帮助用户获得更深入的了解向量空间的结构。此外，我们提出了三个初步的设计，以支持这些任务。
The use of word vector embeddings as the basis for many upstream tasks in text processing has lead to large improvements in accuracy. However, the exact reasons for this success largely remain unclear, as the properties and relations that these embeddings encode are often not well understood. Our goal in this ongoing project is to design effective interactive visualizations that help practitioners and researchers understand and compare such spaces better. The initial steps we have taken is to review relevant literature to identify properties and relations of word vectors that are important for various applications. From these, we derive basic tasks to inform the design of adequate and effective interactive visualizations that help users gain deeper insights into the structure of vector spaces. In addition, we present three initial designs to support these tasks.