CMNIE：中文军事新闻信息抽取基准
原标题：CMNIE: An Information Extraction Benchmark for Chinese Military News
AI 摘要
研究者发布 CMNIE，一个面向中文军事新闻的信息抽取基准数据集，联合标注了事件触发词、事件论元、命名实体和实体关系四层信息。数据集包含 13,000 条来自公开中文军事新闻的实例，人工标注了 7 种事件类型、10 种论元角色、7 种实体类型和 8 种关系类型。实验显示监督模型、零样本大模型和微调大模型在该基准上仍具挑战性，尤其在关系抽取和事件论元跨度精确匹配上，零样本大模型常能识别语义单元但无法精确匹配金标跨度边界。
正文节选
CMNIE: An Information Extraction Benchmark for Chinese Military News Abstract Structured extraction from Chinese military news supports intelligence analysis, decision-making, and knowledge base construction. However, existing resources provide limited support for joint information extraction in this domain, especially when events, event arguments, entities, and relations must be modeled together. We present CMNIE, an information extraction benchmark for Chinese military news. Extending military