用句子排序精简长文档，零样本实现高效分类
Efficient Zero-Shot Long Document Classification by Reducing Context Through Sentence Ranking
- 基于TF-IDF筛选最相关句子，压缩输入上下文
- 仅保留前50%高分句仍保持接近全文档性能
- 适合无标注数据的长文本分类任务
基于Transformer的模型如BERT在短文本分类上表现优异，但在长文档分类（LDC）中受限于输入长度和计算效率。本文提出一种高效零样本长文档分类方法，通过句子排序减少上下文，不改变模型结构。该方法利用TF-IDF策略选取最具信息量的句子，使原本训练于短文本（如标题）的模型可适配长文档。在马拉地语新闻数据集MahaNews上，评估了三种上下文压缩策略，结果表明仅保留排名前50%的句子，即可维持与完整文档推理相当的分类准确率，同时将推理时间缩短最高达35%。这证明句子排序是实现可扩展、高效的零样本长文档分类的简单有效方法。
原文摘要 · Abstract (English)
Transformer-based models like BERT excel at short text classification but struggle with long document classification (LDC) due to input length limitations and computational inefficiencies. In this work, we propose an efficient, zero-shot approach to LDC that leverages sentence ranking to reduce input context without altering the model architecture. Our method enables the adaptation of models trained on short texts, such as headlines, to long-form documents by selecting the most informative sentences using a TF-IDF-based ranking strategy. Using the MahaNews dataset of long Marathi news articles, we evaluate three context reduction strategies that prioritize essential content while preserving classification accuracy. Our results show that retaining only the top 50\% ranked sentences maintains performance comparable to full-document inference while reducing inference time by up to 35\%. This demonstrates that sentence ranking is a simple yet effective technique for scalable and efficient zero-shot LDC.
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。