We propose a fully unsupervised method to detect bias in contextualized embeddings. The method leverages the assortative information latently encoded by social networks and combines orthogonality regularization, structured sparsity learning, and graph neural networks to find the embedding subspace capturing this information. As a concrete example, we focus on the phenomenon of ideological bias: we introduce the concept of an ideological subspace, show how it can be found by applying our method to online discussion forums, and present techniques to probe it. Our experiments suggest that the ideological subspace encodes abstract evaluative semantics and reflects changes in the political left-right spectrum during the presidency of Donald Trump.

我们提出了一种完全无监督的方法来检测上下文嵌入中的偏差。该方法利用社交网络中隐含的同质性信息，并结合正交性正则化、结构稀疏学习和图神经网络来发现捕捉这些信息的嵌入子空间。在具体的例子中，我们关注意识形态偏差现象：我们引入了意识形态子空间的概念，展示了如何将我们的方法应用于在线讨论论坛来找到它，并提出了探究它的技术。我们的实验表明，意识形态子空间编码抽象的评价语义，反映了唐纳德·特朗普总统任期期间政治左右谱的变化。

无监督检测上下文嵌入偏差及其对意识形态的应用