论文标题
在多模式临床NLP中探索特定文本和黑框公平算法
Exploring Text Specific and Blackbox Fairness Algorithms in Multimodal Clinical NLP
论文作者
论文摘要
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Freetext）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，辩论性的单词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绩效平衡和公平的经典概念。我们希望我们的论文在临床NLP和公平性的关键交集中激发未来的贡献。完整的源代码可在此处找到：https：//github.com/johntiger1/multimodal_fairness
Clinical machine learning is increasingly multimodal, collected in both structured tabular formats and unstructured forms such as freetext. 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 and classical notions of fairness. We hope that our paper inspires future contributions at the critical intersection of clinical NLP and fairness. The full source code is available here: https://github.com/johntiger1/multimodal_fairness
