首页|期刊导航|新疆大学学报(自然科学版中英文)|融合逻辑约束的全局-局部协同长文本知识抽取方法

融合逻辑约束的全局-局部协同长文本知识抽取方法OA

A Logic-Constrained Global-Local Collaborative Method for Long-Text Knowledge Extraction

中文摘要英文摘要

长文本知识抽取中,语义依赖跨度大、实体指代分散,易导致常规滑动窗口切分破坏跨段语义联系,影响抽取结果的完整性与一致性.针对这一问题,本文提出一种融合逻辑约束的全局-局部协同长文本知识抽取方法(Global-Local Collaborative Knowledge Extraction,GlocalKE).该方法首先在全文范围内利用共指消解整合分散的实体表达,形成可跨窗口传递的全局语义索引;随后引入模糊证据匹配,对生成结果与原文支撑片段间的一致性进行校验,以降低生成式模型产生幻觉的风险;最后结合实体对齐与双向软逻辑推理机制,在本体约束下对候选三元组进行统一校验和修正.在DuIE-Doc和CS-Cn-50两个数据集上的实验表明,所提方法的F1值分别达到65.92%和42.55%,均优于对比基线方法,有效提升长文本知识抽取的准确性与逻辑一致性.

In long-text knowledge extraction,long-span semantic dependencies and dispersed entity references often cause conventional sliding-window segmentation to break cross-paragraph semantic links,thereby affecting the completeness and consistency of extraction results.To address this problem,this paper proposes GlocalKE(Global-Local Collaborative Know-ledge Extraction),a logic-constrained global-local collaborative method for long-text knowledge extraction.The method first uses coreference resolution over the full text to integrate dispersed entity expressions and form a global semantic index that can be transferred across windows.It then introduces fuzzy evidence matching to verify the consistency between generated re‐sults and supporting spans in the original text,reducing the risk of hallucination in generative models.Finally,entity align‐ment and bidirectional soft logic reasoning are combined to check and revise candidate triples under ontology constraints.Ex‐periments on the DuIE-Doc and CS-Cn-50 datasets show that the F1 values of the proposed method reach 65.92%and 42.55%,respectively,and outperform those of the compared baseline methods,improving the accuracy and logical consis‐tency of long-text knowledge extraction.

康生国;秦继伟;张莉

新疆大学 计算机科学与技术学院,新疆 乌鲁木齐 830017||新疆多模态智能处理与信息安全工程技术研究中心,新疆 乌鲁木齐 830017新疆大学 计算机科学与技术学院,新疆 乌鲁木齐 830017||新疆多模态智能处理与信息安全工程技术研究中心,新疆 乌鲁木齐 830017新疆大学 计算机科学与技术学院,新疆 乌鲁木齐 830017||新疆多模态智能处理与信息安全工程技术研究中心,新疆 乌鲁木齐 830017

信息技术与安全科学

知识抽取长文本建模全局-局部协同逻辑约束大语言模型

knowledge extractionlong-text modelingglobal-local collaborationlogic-constrainedlarge language models

《新疆大学学报(自然科学版中英文)》 2026 (5)

546-561,16

新疆战略人才培养计划一流科技领军人才项目"跨媒体知识聚合方法研究与应用"(XJRC-2025-KJ-PY-KJLJ-046).

10.13568/j.cnki.651094.651316.2026.02.07.0002

评论