本体引导的多智能体从学术评论文本中提取评价对象：来自中国图书馆与信息科学的证据
Ontology-Guided Multi-Agent Extraction of Evaluation Objects from Academic Review Texts: Evidence from Chinese Library and Information Science
查看机构详情
- Nanjing University（南京大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对学术评论文本中评价对象抽取效果差的问题，提出本体引导的多智能体框架，在中文图书馆与信息科学数据上取得优于基线的性能，为相关研究评价和情报挖掘提供方法支持。
中文摘要 AI 辅助
学术评论、学术述评和书评是关于理论、方法、文献、机构和政策的评价陈述来源，为学术评价提供了有价值的证据。现有的科学实体抽取方法主要针对研究论文，对评价对象的效果较差，评价对象往往是抽象的、依赖上下文的，且具有模糊的类型边界。本研究提出了一种本体引导的多智能体（multi-agent）评价对象抽取框架，该框架结合了候选发现、本体约束分类和领域审查。实验结果显示，该框架的精确率（Precision）达到90.33%、召回率（Recall）为84.55%、实体级F1值（Entity-level F1）为87.34%、严格类型F1值（Strict Typed F1）为79.78%、类型准确率（Type Accuracy）为91.35%，显著优于基于规则的基线和零样本（zero-shot）基线。消融实验结果表明，多智能体工作流程可提升召回率和稳定性，而基于本体的边界约束可增强细粒度分类并减少类别混淆。该框架支持评价类学术文本的结构化利用，为循证研究评价和科技情报（STI）挖掘提供了方法学支持。
英文摘要
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.
