On Evaluation of Document Classification using RVL-CDIP

CoRR(2023)

引用 0|浏览1
暂无评分
摘要
The RVL-CDIP benchmark is widely used for measuring performance on the task of document classification. Despite its widespread use, we reveal several undesirable characteristics of the RVL-CDIP benchmark. These include (1) substantial amounts of label noise, which we estimate to be 8.1% (ranging between 1.6% to 16.9% per document category); (2) presence of many ambiguous or multi-label documents; (3) a large overlap between test and train splits, which can inflate model performance metrics; and (4) presence of sensitive personally-identifiable information like US Social Security numbers (SSNs). We argue that there is a risk in using RVL-CDIP for benchmarking document classifiers, as its limited scope, presence of errors (state-of-the-art models now achieve accuracy error rates that are within our estimated label error rate), and lack of diversity make it less than ideal for benchmarking. We further advocate for the creation of a new document classification benchmark, and provide recommendations for what characteristics such a resource should include.
更多
查看译文
关键词
document classification,evaluation,rvl-cdip
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要