VERB: Visualizing and Interpreting Bias Mitigation Techniques Geometrically for Word Representations
VERB: Visualizing and Interpreting Bias Mitigation Techniques Geometrically for Word Representations
复制标题
DOI：
10.1145/3604433
复制
发表时间：
2023-06
影响因子：
3.4
通讯作者：
Archit Rathore;Yan Zheng;Chin-Chia Michael Yeh
中科院分区：
文献类型：
--
作者：
Archit Rathore;Yan Zheng;Chin-Chia Michael Yeh
已显示单词矢量嵌入可以包含并扩增其从中提取的数据中的偏差。因此，已经提出了许多技术来识别，减轻和衰减单词表示中的这些偏见。在本文中，我们利用交互式可视化来增加最先进的伪造技术集合的解释性和可访问性。为了帮助这一点，我们介绍了嵌入式表示形式（动词）系统的可视化，这是一种基于开源Web的可视化工具，可帮助用户获得对磁性技术的内部工作的技术理解和视觉直觉，重点关注他们几何特性。特别是，动词提供了易于遵循的示例，探讨了这些偏见技术对高维单词矢量几何形状的影响。为了帮助了解各种偏见技术如何改变潜在的几何形状，动词将每种技术分解为原始变换的可解释序列，并使用降低性降低和交互式视觉探索突出了它们对矢量一词的影响。动词旨在针对自然语言处理（NLP）从业人员，他们正在词嵌入式设计决策系统，以及与NLP机器学习系统公平和道德合作的研究人员。它还可以作为教育的视觉媒介，这有助于NLP新手理解和减轻单词嵌入的偏见。
Word vector embeddings have been shown to contain and amplify biases in the data they are extracted from. Consequently, many techniques have been proposed to identify, mitigate, and attenuate these biases in word representations. In this article, we utilize interactive visualization to increase the interpretability and accessibility of a collection of state-of-the-art debiasing techniques. To aid this, we present the Visualization of Embedding Representations for deBiasing (VERB) system, an open-source web-based visualization tool that helps users gain a technical understanding and visual intuition of the inner workings of debiasing techniques, with a focus on their geometric properties. In particular, VERB offers easy-to-follow examples that explore the effects of these debiasing techniques on the geometry of high-dimensional word vectors. To help understand how various debiasing techniques change the underlying geometry, VERB decomposes each technique into interpretable sequences of primitive transformations and highlights their effect on the word vectors using dimensionality reduction and interactive visual exploration. VERB is designed to target natural language processing (NLP) practitioners who are designing decision-making systems on top of word embeddings and researchers working with the fairness and ethics of machine learning systems in NLP. It can also serve as a visual medium for education, which helps an NLP novice understand and mitigate biases in word embeddings.