Parallax: Visualizing and Understanding the Semantics of Embedding Spaces via Algebraic Formulae
Parallax: Visualizing and Understanding the Semantics of Embedding Spaces via Algebraic Formulae
复制标题
视差：通过代数公式可视化和理解嵌入空间的语义
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Jiawei Zhang
中科院分区：
文献类型：
--
作者：
Piero Molino;Yang Wang;Jiawei Zhang
嵌入是许多现代机器学习和自然语言处理模型的基本组成部分。理解它们并将其可视化对于收集有关它们捕获的信息和模型行为的见解至关重要。在本文中，我们介绍了视差，明确设计用于此任务的工具。视差允许用户使用最先进的嵌入分析方法（PCA和t-SNE）和简单而有效的面向任务的方法，用户可以通过代数公式明确定义投影的轴。%在于将它们投影在二维平面中，而没有与投影轴相关联的任何可解释的语义，这使得多组嵌入之间的详细分析和比较具有挑战性。在这种方法中，嵌入被投影到一个语义上有意义的子空间，这增强了可解释性，并允许更细粒度的分析。我们通过一系列的案例研究和用户研究展示了该工具的强大功能和所提出的方法。
Embeddings are a fundamental component of many modern machine learning and natural language processing models. Understanding them and visualizing them is essential for gathering insights about the information they capture and the behavior of the models. In this paper, we introduce Parallax, a tool explicitly designed for this task. Parallax allows the user to use both state-of-the-art embedding analysis methods (PCA and t-SNE) and a simple yet effective task-oriented approach where users can explicitly define the axes of the projection through algebraic formulae. %consists in projecting them in two-dimensional planes without any interpretable semantics associated to the axes of the projection, which makes detailed analyses and comparison among multiple sets of embeddings challenging. In this approach, embeddings are projected into a semantically meaningful subspace, which enhances interpretability and allows for more fine-grained analysis. We demonstrate the power of the tool and the proposed methodology through a series of case studies and a user study.
DOI：
10.1073/pnas.1720347115
发表时间：
2018-04-17
影响因子：
11.1
作者：
Garg, Nikhil;Schiebinger, Londa;Zou, James
通讯作者：
Zou, James