仅用文件名实现快速高精度文档分类，效率提升442倍。
Document Classification using File Names
- 基于TF-IDF的轻量级文本提取，结合监督学习模型分析文件名。
- 在两个数据集上准确率达99.63%和96.57%，覆盖超90%目标文档。
- 适合数字取证等对速度敏感的场景，显著降低计算开销。
快速文档分类在数字取证和大规模媒体分类等时效性场景中至关重要。传统依赖深度学习模型的方法因推理时间长、计算资源消耗大而难以应对海量文档。本文提出一种轻量级监督学习方法，结合基于TF-IDF的分词技术，仅凭文件名即可高效准确地分类文档，大幅缩短推理时间。实验表明，该方法在两个数据集上对超过90%的待分类文档实现99.63%和96.57%的准确率，相比DiT等复杂模型提速442倍。该方案为关键场景下大规模文档处理提供了高效可靠的解决方案。
原文摘要 · Abstract (English)
Rapid document classification is critical in several time-sensitive applications like digital forensics and large-scale media classification. Traditional approaches that rely on heavy-duty deep learning models fall short due to high inference times over vast input datasets and computational resources associated with analyzing whole documents. In this paper, we present a method using lightweight supervised learning models, combined with a TF-IDF feature extraction-based tokenization method, to accurately and efficiently classify documents based solely on file names, that substantially reduces inference time. Our results indicate that file name classifiers can process more than 90% of in-scope documents with 99.63% and 96.57% accuracy when tested on two datasets, while being 442x faster than more complex models such as DiT. Our method offers a crucial solution to efficiently process vast document datasets in critical scenarios, enabling fast and more reliable document classification.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。