论文标题
NLP模型中的社会偏见是残疾人的障碍
Social Biases in NLP Models as Barriers for Persons with Disabilities
论文作者
论文摘要
建立公平和包容的NLP技术需要考虑ML模型中是否代表社会态度。特别是，在模型中编码的表示形式通常会无意间从训练的数据中永久存在不良的社会偏见。在本文中，我们提供了在两种不同的英语模型中提到残疾的不良偏见的证据：毒性预测和情感分析。接下来，我们证明是大多数NLP管道中关键第一步的神经嵌入，同样包含不受欢迎的偏见。最后，我们强调有关残疾的话语中的局部偏见，这可能导致观察到的模型偏见。例如，在讨论精神疾病的文本中，枪支暴力，无家可归和吸毒成瘾过多。
Building equitable and inclusive NLP technologies demands consideration of whether and how social attitudes are represented in ML models. In particular, representations encoded in models often inadvertently perpetuate undesirable social biases from the data on which they are trained. In this paper, we present evidence of such undesirable biases towards mentions of disability in two different English language models: toxicity prediction and sentiment analysis. Next, we demonstrate that the neural embeddings that are the critical first step in most NLP pipelines similarly contain undesirable biases towards mentions of disability. We end by highlighting topical biases in the discourse about disability which may contribute to the observed model biases; for instance, gun violence, homelessness, and drug addiction are over-represented in texts discussing mental illness.
