论文标题
揭露上下文刻板印象：测量和减轻伯特的性别偏见
Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias
论文作者
论文摘要
上下文化的单词嵌入已取代标准嵌入，作为NLP系统中选择的代表性知识来源。由于先前在标准单词嵌入中发现了多种偏见，因此评估其替代品中编码的偏见至关重要。为了关注伯特（Devlin等，2018），我们通过研究占性别否定的目标词与英语和德语职业名称之间的关联来衡量性别偏见，并将发现与现实世界中的劳动力统计数据进行比较。在应用反事实数据替换（CDS）之后，我们通过对GAP语料库进行微调Bert（Webster等，2018）来减轻偏见（Maudslay等，2019）。我们表明，我们测量偏见的方法适用于诸如英语之类的语言，但不适合具有丰富形态和性别标记的语言，例如德语。我们的结果强调了在跨语言上研究偏见和缓解技术的重要性，尤其是考虑到当前强调大规模，多语言模型的重点。
Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems. Since a variety of biases have previously been found in standard word embeddings, it is crucial to assess biases encoded in their replacements as well. Focusing on BERT (Devlin et al., 2018), we measure gender bias by studying associations between gender-denoting target words and names of professions in English and German, comparing the findings with real-world workforce statistics. We mitigate bias by fine-tuning BERT on the GAP corpus (Webster et al., 2018), after applying Counterfactual Data Substitution (CDS) (Maudslay et al., 2019). We show that our method of measuring bias is appropriate for languages such as English, but not for languages with a rich morphology and gender-marking, such as German. Our results highlight the importance of investigating bias and mitigation techniques cross-linguistically, especially in view of the current emphasis on large-scale, multilingual language models.
