Warning: This paper contains examples of offensive language, including insulting or objectifying expressions.

Various existing studies have analyzed what social biases are inherited by NLP models. These biases may directly or indirectly harm people, therefore previous studies have focused only on human attributes. However, until recently no research on social biases in NLP regarding nonhumans existed. In this paper,¹ we analyze biases to nonhuman animals, i.e. speciesist bias, inherent in English Masked Language Models such as BERT. We analyzed speciesist bias against 46 animal names using template-based and corpus-extracted sentences containing speciesist (or non-speciesist) language. We found that pre-trained masked language models tend to associate harmful words with nonhuman animals and have a bias toward using speciesist language for some nonhuman animal names. Our code for reproducing the experiments will be made available on GitHub.²

警告：本文包含攻击性语言的示例，包括侮辱性或客观化表达。

现有的各种研究分析了 NLP 模型继承了哪些社会偏见。这些偏见可能直接或间接地伤害人，因此以前的研究只关注人的属性。然而，直到最近，还没有关于 NLP 中关于非人类的社会偏见的研究。在本文中，¹我们分析了对非人类动物的偏见，即物种偏见，这是 BERT 等英语蒙面语言模型所固有的。我们使用包含物种歧视（或非物种歧视）语言的基于模板和语料库提取的句子分析了对 46 个动物名称的物种歧视偏见。我们发现，预先训练的蒙面语言模型倾向于将有害词与非人类动物联系起来，并且偏向于对一些非人类动物名称使用物种歧视语言。我们用于重现实验的代码将在 GitHub 上提供。²