基于Tobacco-3482和RVL-CDIP的文本分类器的分布外泛化研究
Exploring Out-of-Distribution Generalization in Text Classifiers Trained on Tobacco-3482 and RVL-CDIP
摘要：
为了足够强大以广泛采用，涉及机器学习模型的文档分析系统必须能够正确响应落在用于生成模型所训练的数据的数据分布之外的输入。本文探讨了在标准文档分类数据集上训练的文本分类器在推理时推广到非分布文档的能力。我们以Tobacco-3482和RVL-CDIP数据集为起点，生成新的分布外评估数据集，以分析在这些标准数据集上训练的模型的泛化性能。我们发现，在较小的Tobacco-3482数据集上训练的模型在我们新的分布外数据上表现不佳，而在较大的RVL-CDIP上训练的文本分类模型表现出较小的性能下降。
英文摘要：
To be robust enough for widespread adoption, document analysis systems involving machine learning models must be able to respond correctly to inputs that fall outside of the data distribution that was used to generate the data on which the models were trained. This paper explores the ability of text classifiers trained on standard document classification datasets to generalize to out-of-distribution documents at inference time. We take the Tobacco-3482 and RVL-CDIP datasets as a starting point and generate new out-of-distribution evaluation datasets in order to analyze the generalization performance of models trained on these standard datasets. We find that models trained on the smaller Tobacco-3482 dataset perform poorly on our new out-of-distribution data, while text classification models trained on the larger RVL-CDIP exhibit smaller performance drops.
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。
