论文标题
单词嵌入的联合多类辩护
Joint Multiclass Debiasing of Word Embeddings
论文作者
论文摘要
单词嵌入的偏见一直是最近感兴趣的主题，以及其减少努力。当前的方法表明，在诸如性别或种族之类的单一偏见维度方面取得了有希望的进步。在本文中，我们提出了一种共同的多类辩护方法，该方法能够同时使用多个偏差维度。在这个方向上，我们提出了两种方法，即硬麦和软武器，旨在通过最大程度地减少嵌入嵌入协会测试（WEAT）的分数来减少偏见。我们通过将单词嵌入在三种不同的偏见（宗教，性别和种族）上的单词嵌入来证明我们的方法的生存能力，并表明我们的概念可以减少甚至完全消除偏见，同时保持词语中的向量之间有意义的关系。我们的工作为文本数据的更公正的神经表示增强了基础。
Bias in Word Embeddings has been a subject of recent interest, along with efforts for its reduction. Current approaches show promising progress towards debiasing single bias dimensions such as gender or race. In this paper, we present a joint multiclass debiasing approach that is capable of debiasing multiple bias dimensions simultaneously. In that direction, we present two approaches, HardWEAT and SoftWEAT, that aim to reduce biases by minimizing the scores of the Word Embeddings Association Test (WEAT). We demonstrate the viability of our methods by debiasing Word Embeddings on three classes of biases (religion, gender and race) in three different publicly available word embeddings and show that our concepts can both reduce or even completely eliminate bias, while maintaining meaningful relationships between vectors in word embeddings. Our work strengthens the foundation for more unbiased neural representations of textual data.
