提出文本到模式图的基准与可审计管道，解决知识抽取中的模式构建瓶颈。
SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text
- 构建基于24个数据源的纯文本模式诱导基准SCOPE，支持事件类型与角色抽取。
- SCION管道在多种指标下超越现有方法，实现最高F1值，且可追溯每步决策证据。
- 适合需要可解释、可验证模式构建流程的研究者与工业应用开发者。
模式图是基于模式的信息抽取和知识图谱构建的上游瓶颈，但多数抽取系统假设模式已存在。我们提出SCOPE（模式构建与本体归纳管道评估），一个仅使用训练文本的基准，用于从原始文本中进行模式诱导及可选的模式融合，基于24个公开信息抽取源（15个关系抽取、9个事件抽取）构建，统一为仅用于评估的黄金模式图；核心事件抽取目标涵盖事件类型与事件内论元角色，事件间链接单独报告。我们提出SCION（模式构建与归纳的本体归一化），一种可审计的参考管道而非新型抽取架构；它从训练文本构建候选空间，并严格限制命名、合并、过滤、验证与保守融合操作，所有操作均基于候选链接的证据，遵循严格的JSON契约。在SCOPE核心套件上，SCION-lite在字面、模糊、连续与图结构等模式图指标下，超越已发布的源模式参考、Text2Onto风格、仅大模型及匹配提取后聚合基线，达到最高F1值；而紧凑的开源模型版本SCION-RL降低了对专有大模型模式工程师的依赖。结果针对归一化的类型边目标报告，而非声称诱导模式优于人工本体设计。发布内容包括证据关联输出、解析/回退日志、候选保留/合并日志、运行清单、代码与基准包，详见https://github.com/wandugu/paper_scion。
原文摘要 · Abstract (English)
Schema graphs are an upstream bottleneck of schema-grounded information extraction and knowledge graph construction, yet most extraction systems assume the schema is already available. We introduce SCOPE (Schema Construction and Ontology-induction Pipeline Evaluation), a train-text-only benchmark for corpus-to-schema induction and optional schema fusion from raw text, built from 24 public information extraction sources (15 RE and 9 EE) normalized into evaluation-only gold schema graphs; its core event-extraction target covers event types and within-event argument roles, with inter-event links reported separately. We present SCION (Schema Construction and Induction with Ontology Normalization), an auditable reference pipeline rather than a new extraction architecture; it constructs candidate spaces from train text and restricts naming, merging, filtering, validation, and conservative fusion to candidate-linked evidence under strict JSON contracts. On the SCOPE core suite, SCION-lite attains the highest F1 among released source-schema references, Text2Onto-style, LLM-only, and matched extract-then-aggregate baselines under Literal, Fuzzy, Continuous, and Graph schema-graph metrics, while the compact open-model SCION-RL variant reduces reliance on proprietary LLM schema engineers. These results are reported against normalized typed-edge targets rather than as claims that induced schemas surpass human ontology design; the release includes evidence-linked outputs, parse/fallback logs, candidate retention/merging logs, run manifests, code, and benchmark packages at https://github.com/wandugu/paper_scion.
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。