用大模型自动构建知识图谱，提升复杂句子理解与关系抽取效果
Automated Knowledge Graph Construction using Large Language Models and Sentence Complexity Modelling
- 结合共指消解与句法分解，实现端到端句子级知识图谱构建
- 关系抽取在REBEL上达65.8%宏F1，较之前提升8个百分点
- 开源超15万三元组数据集，适合知识工程与自然语言处理研究者
我们提出CoDe-KG，一个开源的端到端知识图谱构建流水线，融合鲁棒的共指消解与句法分解技术。基于该模型，我们构建了一个包含超过15万条知识三元组的数据集并公开发布。同时贡献了7248行用于句法复杂度建模的训练语料，190行共指消解的金标准人工标注（来自PubMed开源肺癌摘要），900行句子转换策略的人工标注，以及398条三元组的金标准标注。系统性筛选五类复杂度下的最优提示-模型组合，发现混合思维链与少样本提示可使句子简化任务达到99.8%精确匹配准确率。在关系抽取任务中，该流水线在REBEL上取得65.8%宏F1，比前序最佳结果高出8个百分点；在WebNLG2上达到75.7%微F1，且在Wiki-NRE和CaRB上表现持平或超越。消融实验表明，整合共指消解与句法分解可使罕见关系的召回率提升超过20%。代码与数据集已开放于https://github.com/KaushikMahmud/CoDe-KG_EMNLP_2025。
原文摘要 · Abstract (English)
We introduce CoDe-KG, an open-source, end-to-end pipeline for extracting sentence-level knowledge graphs by combining robust coreference resolution with syntactic sentence decomposition. Using our model, we contribute a dataset of over 150,000 knowledge triples, which is open source. We also contribute a training corpus of 7248 rows for sentence complexity, 190 rows of gold human annotations for co-reference resolution using open source lung-cancer abstracts from PubMed, 900 rows of gold human annotations for sentence conversion policies, and 398 triples of gold human annotations. We systematically select optimal prompt-model pairs across five complexity categories, showing that hybrid chain-of-thought and few-shot prompting yields up to 99.8% exact-match accuracy on sentence simplification. On relation extraction (RE), our pipeline achieves 65.8% macro-F1 on REBEL, an 8-point gain over the prior state of the art, and 75.7% micro-F1 on WebNLG2, while matching or exceeding performance on Wiki-NRE and CaRB. Ablation studies demonstrate that integrating coreference and decomposition increases recall on rare relations by over 20%. Code and dataset are available at https://github.com/KaushikMahmud/CoDe-KG_EMNLP_2025
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。