跳转至

COCI：会议组织者与内容标识符

文章背景与核心概要

在学术交流中，诸如论文征集（Calls for Papers, CfPs）等非正式的灰色文献发挥着至关重要的作用，然而它们长期以来却与现代学术知识图谱（Scholarly Knowledge Graphs）处于割裂状态。由于这些文档具有非结构化且高度异构的特点，传统的大规模处理方法一直举步维艰。本文介绍了一种名为 COCI（Conference Organisers and Content Identifier）的 AI 驱动框架，旨在解决这一痛点。

COCI 采用了一个多阶段流水线（Multi-stage Pipeline），将大语言模型（LLMs）与语义映射技术相结合，能够从原始的 CfP 文本中提取出细粒度、结构化的元数据。通过实现作者消歧（Author Disambiguation）以及主题和会议系列的语义对齐，COCI 成功打通了非正式学术传播与结构化语义网资源之间的壁垒，为系统化分析非出版商主导的学术活动奠定了坚实的基础。该论文已被 ISWC 2026 接收为演示论文（Demo paper）。

Summary (摘要与概述)

The Conference Organisers and Content Identifier (COCI) is an AI-driven framework designed to bridge the gap between informal scholarly grey literature—specifically Calls for Papers (CfPs)—and modern Scholarly Knowledge Graphs. By utilizing a multi-stage pipeline combining Large Language Models (LLMs) and semantic mapping techniques, COCI extracts fine-grained structured metadata from raw CfP texts. It enables author disambiguation and semantically aligns topics and conference series with major established knowledge bases (including OpenAlex, DBLP, TIB ConfIDent, and the AIDA Dashboard), laying the groundwork for the systematic analysis of non-publisher-based academic events.

会议组织者与内容标识符（COCI）是一个人工智能驱动的框架，旨在弥合非正式学术灰色文献（特别是论文征集 CfPs）与现代学术知识图谱之间的鸿沟。通过利用结合了大语言模型（LLMs）和语义映射技术的多阶段流水线，COCI 从原始的 CfP 文本中提取出细粒度的结构化元数据。它能够进行作者消歧，并将主题和会议系列与主流的既定知识库（包括 OpenAlex、DBLP、TIB ConfIDent 和 AIDA Dashboard）进行语义对齐，为系统分析非出版商主导的学术活动奠定了基础。

Metadata (元数据)

Authors (作者)

  • Angelo Salatino
  • Francesco Osborne
  • Alexis Vizcaino
  • Aliaksandr Birukou
  • Enrico Motta
  • Angelo Salatino
  • Francesco Osborne
  • Alexis Vizcaino
  • Aliaksandr Birukou
  • Enrico Motta

Abstract (摘要)

Despite the critical role of grey literature in scholarly communication, artefacts such as Calls for Papers (CfPs) remain largely isolated from modern Scholarly Knowledge Graphs. The unstructured and highly heterogeneous nature of these documents has traditionally hindered their large-scale processing. In this demo paper, we present the Conference Organisers and Content Identifier (COCI), an AI-based framework designed to extract fine-grained, structured metadata from raw CfP texts. COCI employs a multi-stage pipeline that combines Large Language Models (LLMs) with semantic mapping techniques to integrate extracted entities with established knowledge bases, including OpenAlex, DBLP, TIB ConfIDent, and the AIDA Dashboard. By disambiguating authors and semantically aligning topics and conference series, COCI bridges the gap between informal scholarly dissemination and structured Semantic Web resources, laying the foundation for systematic analysis of non-publisher-based academic events.

尽管灰色文献在学术交流中发挥着关键作用，但诸如论文征集（CfPs）等产物在很大程度上仍然与现代学术知识图谱相隔离。这些文档非结构化且高度异构的特性，传统上阻碍了对其进行大规模处理。在这篇演示论文中，我们提出了会议组织者与内容标识符（COCI），这是一个基于人工智能的框架，旨在从原始的 CfP 文本中提取细粒度的结构化元数据。COCI 采用了一个多阶段流水线，将大语言模型（LLMs）与语义映射技术相结合，将提取出的实体与既定知识库（包括 OpenAlex、DBLP、TIB ConfIDent 和 AIDA Dashboard）进行整合。通过对作者进行消歧并对主题和会议系列进行语义对齐，COCI 架起了非正式学术传播与结构化语义网资源之间的桥梁，为系统分析非出版商主导的学术活动奠定了基础。

Full-Text & Access Links (全文与访问链接)

External References & Tools (外部参考与工具)