CodeKGC: 基于代码的生成式知识图谱构建模型（英文版）

英文标题：CodeKGC: Code Language Model for Generative Knowledge Graph Construction中文摘要：通过代码语言模型生成三元组以构建语义结构明确的知识图谱，并使用增强理由生成法提高知识提取能力，实验结果表明该方法在基准数据集上取得优异表现。英文摘要：Current generative knowledge graph construction approaches usually fail tocapture structural knowledge by simply flattening natural language intoserialized texts or a specification language. However, large generativelanguage model trained on structured data such as code has demonstratedimpressive capability in understanding natural language