arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.01326cs.CLcs.AI
收藏

保姆的女人:论语言生成中的偏见

The Woman Worked as a Babysitter: On Biases in Language Generation

Information Sciences Institute, University of Southern California(南加州大学信息科学研究所);University of California, Los Angeles(加州大学洛杉矶分校)

Emily Sheng, Kai-Wei Chang, Premkumar Natarajan, Nanyun Peng

摘要:

我们提出了一个系统的研究,在自然语言生成(NLG)的偏见,通过分析文本生成的提示,包含提到不同的人口群体。在这项工作中,我们引入了对人口统计的概念,使用不同程度的考虑对不同的人口统计作为一个定义性的指标,在NLG的偏见,并分析在何种程度上的情绪分数是一个相关的代理度量方面。为此,我们从语言模型中收集策略生成的文本,并使用情感和关注分数手动注释文本。此外,我们通过迁移学习建立了一个自动的关注分类器,这样我们就可以分析看不见的文本中的偏见。总之,这些方法揭示了语言模型生成的偏见性质的程度。我们的分析提供了一个研究的偏见NLG,偏见指标和相关的人类判断,以及经验证据的有用性,我们的注释数据集。

英文摘要:

We present a systematic study of biases in natural language generation (NLG) by analyzing text generated from prompts that contain mentions of different demographic groups. In this work, we introduce the notion of the regard towards a demographic, use the varying levels of regard towards different demographics as a defining metric for bias in NLG, and analyze the extent to which sentiment scores are a relevant proxy metric for regard. To this end, we collect strategically-generated text from language models and manually annotate the text with both sentiment and regard scores. Additionally, we build an automatic regard classifier through transfer learning, so that we can analyze biases in unseen text. Together, these methods reveal the extent of the biased nature of language model generations. Our analysis provides a study of biases in NLG, bias metrics and correlated human judgments, and empirical evidence on the usefulness of our annotated dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑