English(EN) Using Embedding Models to Improve Probabilistic Race Prediction

嵌入模型增强了对不常见姓氏的种族预测

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-24 13:49

研究人员开发了一种由嵌入驱动的方法来改进概率种族预测，解决了现有方法（如贝叶斯改进姓氏地理编码 (BISG)）的局限性。标准的 BISG 依赖于遗漏不常见姓氏的人口普查数据，导致对相当一部分人口的性能下降。新方法 eBISG 利用预训练的文本嵌入和神经网络来估计 Census 未覆盖姓氏的种族概率，显示出显著的收益，尤其是在西班牙裔和亚裔个体方面。 AI

影响通过改进对代表性不足的姓氏的种族预测来增强人口统计分析，可能有助于差异研究。

排序理由这是一篇研究论文，详细介绍了一种使用嵌入模型改进种族预测的新方法。

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CL TIER_1 English(EN) · Noan Dasanaike, Kosuke Imai · 2026-04-27 04:00

Using Embedding Models to Improve Probabilistic Race Prediction

arXiv:2604.22555v1 Announce Type: new Abstract: Estimating racial disparity requires individual-level race data, which are often unavailable due to the sensitivity of collecting such information. To address this problem, many researchers utilize Bayesian Improved Surname Geocodin…
arXiv cs.CL TIER_1 English(EN) · Kosuke Imai · 2026-04-24 13:49

Using Embedding Models to Improve Probabilistic Race Prediction

Estimating racial disparity requires individual-level race data, which are often unavailable due to the sensitivity of collecting such information. To address this problem, many researchers utilize Bayesian Improved Surname Geocoding (BISG), which have critically relied on Census…

报道来源 [2]

Using Embedding Models to Improve Probabilistic Race Prediction

Using Embedding Models to Improve Probabilistic Race Prediction

相关实体

相关话题