用知识图谱指导多智能体提取学术评论中的评价对象，提升分析精度。
Ontology-Guided Multi-Agent Extraction of Evaluation Objects from Academic Review Texts: Evidence from Chinese Library and Information Science
- 基于领域本体构建多智能体协同框架，分步完成候选发现与分类。
- 在中文图书情报领域数据上实现87.34%的实体级F1，优于基线模型。
- 适合做学术评价、科技政策分析的研究者使用，支持证据驱动研究。
学术评论、学术评述和书评是关于理论、方法、文献、机构和政策等评价性陈述的重要来源，为学术评估提供宝贵证据。现有科学实体抽取方法主要针对研究论文，在识别评价对象方面表现不佳，因评价对象常具抽象性、依赖上下文且类型边界模糊。本文提出一种基于本体引导的多智能体框架用于评价对象抽取。实验结果表明，该框架在中文图书情报领域数据上达到精确率90.33%、召回率84.55%、实体级F1值87.34%、严格类型F1值79.78%、类型准确率91.35%，显著优于基于规则和零样本的基线方法。消融实验显示，多智能体流程提升了召回率与稳定性，而基于本体的边界约束增强了细粒度分类并减少类别混淆。该框架支持评价性学术文本的结构化利用，为基于证据的科研评估与STI挖掘提供方法支撑。
原文摘要 · Abstract (English)
Academic reviews, scholarly commentaries, and book reviews serve as sources of evaluative statements about theories, methods, literature, institutions, and policies, providing valuable evidence for scholarly evaluation. Existing scientific entity extraction methods mainly target research articles and are less effective for evaluation objects, which are often abstract, context-dependent, and characterized by ambiguous type boundaries. This study proposes an ontology-guided multi-agent framework for evaluation object extraction. The framework combines candidate discovery, ontology-constrained classification, and domain review. Experimental results show that it achieves a Precision of 90.33%, Recall of 84.55%, Entity-level F1 of 87.34%, Strict Typed F1 of 79.78%, and Type Accuracy of 91.35%, substantially outperforming rule-based and zero-shot baselines. Ablation results indicate that the multi-agent workflow improves recall and stability, while ontology-based boundary constraints enhance fine-grained classification and reduce category confusion. The framework supports the structured utilization of evaluative scholarly texts and provides methodological support for evidence-based research evaluation and STI mining.
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。