Measuring Gender Bias in Contextualized Embeddings
Measuring Gender Bias in Contextualized Embeddings
复制标题
衡量情境化嵌入中的性别偏见
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Jesse Shanahan
中科院分区：
文献类型：
--
作者：
Styliani Katsarou;Borja Rodríguez;Jesse Shanahan
：Transformer模型现在越来越多地用于实际应用中。盲目地使用这些模型作为自动化工具可能会以我们没有意识到的方式传播偏见。为了负责任地采取行动来解决这个问题，我们发现和量化这些偏见至关重要。已经开发了鲁棒的方法来测量非情境化嵌入中的偏差。然而，这些方法无法适用于上下文嵌入，由于其可变的性质。我们的研究重点是检测和测量与T5和mT5的嵌入性别相关的刻板偏见。我们通过测量不同职业的T5词嵌入的性别极性来量化偏见。为了衡量性别极性，我们使用了一个稳定的性别方向，我们在模型的嵌入空间中检测到。我们还测量了特定下游任务的性别偏见，并将瑞典语与英语以及T5模型及其多语言变体的各种大小进行了比较。从我们的探索的见解表明，使用一个稳定的性别方向，即使在一个Transformer的可变嵌入空间，可以是一个强大的方法来衡量偏见。我们发现，更高的地位职业与男性性别比女性性别。此外，我们的方法表明，瑞典语与性别相关的偏见比英语少，性别偏见的表现与使用更大的语言模型有关。
: Transformer models are now increasingly being used in real-world applications. Indiscrim-inately using these models as automated tools may propagate biases in ways we do not realize. To responsibly direct actions that will combat this problem, it is of crucial importance that we detect and quantify these biases. Robust methods have been developed to measure bias in non-contextualized embeddings. Nevertheless, these methods fail to apply to contextualized embeddings due to their mutable nature. Our study focuses on the detection and measurement of stereotypical biases associated with gender in the embeddings of T5 and mT5. We quantify bias by measuring the gender polarity of T5’s word embeddings for various professions. To measure gender polarity, we use a stable gender direction that we detect in the model’s embedding space. We also measure gender bias with respect to a specific downstream task and compare Swedish with English, as well as various sizes of the T5 model and its multilingual variant. The insights from our exploration indicate that the use of a stable gender direction, even in a Transformer’s mutable embedding space, can be a robust method to measure bias. We show that higher status professions are associated more with the male gender than the female gender. In addition, our method suggests that the Swedish language carries less bias associated with gender than English, and the higher manifestation of gender bias is associated with the use of larger language models.
DOI：
10.1073/pnas.1720347115
发表时间：
2018-04-17
影响因子：
11.1
作者：
Garg, Nikhil;Schiebinger, Londa;Zou, James
通讯作者：
Zou, James