Artificial intelligence (AI) is increasingly being used in decision making across various
industries, including the public health arena. Bias in any decision‐making process can …

In the applications of machine learning, it is difficult to ensure the quality of training data due
to the various sources of training data and the inexperience of some annotators. By tightly …

Word embedding, a high-dimensional (HD) numerical representation of words generated by
machine learning models, has been used for different natural language processing tasks, for …

在机器学习应用中, 由于数据来源渠道多以及部分标注者水平不足, 训练数据质量很难得到保证.
通过深度结合机器学习和可视化技术, 可视分析技术将人融入数据质量分析与提升回路中 …

Abstract Language models are trained on large text corpora that often include stereotypes.
This can lead to direct or indirect bias in downstream applications. In this work, we present a …

Language models are trained on large text corpora that often include stereotypes. This can
lead to direct or indirect bias in downstream applications. In this work, we present a method …

In den letzten Jahren hat die Bedeutung der Verarbeitung natürlicher Sprache mit immer
mehr Anwendungsbereichen zugenommen. Die zur Transkription der Sprache verwendeten …

Arjun Subramonian (they/them) PhD Student, UCLA NSF MENTOR and Cota-Robles
Fellow Queer in AI Core Organizer These slides contai Page 1 Bias and Power in NLP …

NLP Bias Page 1 Guest Lecture: Bias in NLP Arjun Subramonian (they/them) PhD Student and
Cota-Robles Fellow at UCLA ScAi and NLP Queer in AI Core Organizer These slides contain …