用强化学习实现可调节的文献筛选停止策略，灵活适配不同召回率需求。
A Generalised and Adaptable Reinforcement Learning Stopping Method
- 设计新环境GRLStop，统一建模多种召回目标与成本权衡。
- 在6个基准数据集上验证，相比基线方法更高效且灵活。
- 适合需要自适应筛选策略的法律、医疗等高成本文档审查场景。
本文提出一种基于强化学习的科技辅助审查（TAR）停止方法。以往方法对停止行为控制有限，如固定召回率或无法平衡召回与成本。为此，提出新型强化学习环境GRLStop，使单一模型可适配多种目标召回率，兼顾召回与成本权衡，并集成分类器。在六个基准数据集（CLEF e-Health 2017-2019、TREC Total Recall、TREC Legal、Reuters RCV1）上，多个召回率水平下进行实验，结果表明该方法优于多个基线，同时具备更强灵活性。
原文摘要 · Abstract (English)
This paper presents a Technology Assisted Review (TAR) stopping approach based on Reinforcement Learning (RL). Previous such approaches offered limited control over stopping behaviour, such as fixing the target recall and tradeoff between preferring to maximise recall or cost. These limitations are overcome by introducing a novel RL environment, GRLStop, that allows a single model to be applied to multiple target recalls, balances the recall/cost tradeoff and integrates a classifier. Experiments were carried out on six benchmark datasets (CLEF e-Health datasets 2017-9, TREC Total Recall, TREC Legal and Reuters RCV1) at multiple target recall levels. Results showed that the proposed approach to be effective compared to multiple baselines in addition to offering greater flexibility.
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。