Analyzing Text Specific vs Blackbox Fairness Algorithms in Multimodal Clinical NLP

Analyzing Text Specific vs Blackbox Fairness Algorithms in Multimodal Clinical NLP
复制标题

多模式临床 NLP 中分析文本特定算法与 Blackbox 公平算法

DOI:
10.18653/v1/2020.clinicalnlp-1.33
复制
发表时间:
2020
期刊:
ArXiv
影响因子:
--
通讯作者:
Frank Rudzicz
Frank Rudzicz
中科院分区:
--
文献类型:
--
作者:
John Chen;Ian Berlot;Safwan Hossain;Xindi Wang;Frank Rudzicz

文献摘要

参考文献

被引文献

相似文献

临床机器学习越来越多模式,以结构化表格格式和非结构化形式(例如自由文本)收集。我们提出了一项新的任务,即在多模式临床数据集上探索公平性,对下游医疗预测任务采用均等的赔率。为此,我们研究了处理后处理后的模态性不足的公平算法 - 均衡的赔率 - 并将其与特定于文本的公平算法进行比较:clabiased临床单词嵌入。尽管事实上,辩护单词的嵌入并未明确解决受保护群体的均等几率,但我们表明,特定于文本的公平方法可以同时达到良好的平衡,即良好的表现经典的公平概念。我们的工作为未来在临床NLP和公平性的关键交集中为未来的工作打开了大门。
Clinical machine learning is increasingly multimodal, collected in both structured tabular formats and unstructured forms such as free text. We propose a novel task of exploring fairness on a multimodal clinical dataset, adopting equalized odds for the downstream medical prediction tasks. To this end, we investigate a modality-agnostic fairness algorithm - equalized odds post processing - and compare it to a text-specific fairness algorithm: debiased clinical word embeddings. Despite the fact that debiased word embeddings do not explicitly address equalized odds of protected groups, we show that a text-specific approach to fairness may simultaneously achieve a good balance of performance classical notions of fairness. Our work opens the door for future work at the critical intersection of clinical NLP and fairness.
DOI: 10.1037/hea0000242
发表时间: 2016-04
期刊: Health psychology : official journal of the Division of Health Psychology, American Psychological Association
影响因子: --
作者:
Williams DR;Priest N;Anderson NB
通讯作者: Anderson NB
黑人之于罪犯就像白人之于警察:检测和消除词嵌入中的多类偏差
DOI: --
发表时间: 2019
期刊: 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL
影响因子: --
作者:
Manzini, Thomas;Lim, Yao Chong;Tsvetkov, Yulia;Black, Alan W
通讯作者: Black, Alan W