arXiv cs.CL· Nipun D. Pathirage, Henrique Santos, Deborah L. McGuinness·· 12 小时前AI 评分29
SUDO：从科学论文到全球学术话语的学术上层话语本体
SUDO: From Scientific Publications to Global Scholarly Discourse
AI 导读
研究者提出学术上层话语本体 SUDO，定义知识要素如何组织并关联成论文的研究叙事，使每篇论文的学术话语能自下而上构建为连贯、有来源依据的表示。现有概念中心与陈述中心两类学术知识图谱只保留特定抽取单元可表达的内容，SUDO 则跨论文复用同一结构连接研究叙事，不丢弃局部语境与来源。在多项学术知识建模用例及基于 LLM 的科学问答下游任务上，SUDO 均显示出性能提升。
正文
Abstract:Scholarly Knowledge Graphs (SKGs) support literature search, scientific discovery, and agent-assisted research. Yet, most approaches to SKG construction pre-specify the knowledge unit to be represented, typically named scholarly entities or contribution-level statements, and retain only the publication content expressible through that unit. This choice produces two dominant yet distinct paradigms: concept-centric SKGs that preserve entities and local relations, and statement-centric SKGs that capture high-level discourse in sentences. In both cases, the graph reflects a chosen extraction target rather than how a paper constructs and communicates knowledge. We introduce SUDO, the Scholarly Upper Discourse Ontology, which defines how knowledge elements are organized and related to form a paper's research narrative, namely its scholarly discourse. Using linguistic principles that generalize across fields and tasks, SUDO enables each publication's scholarly discourse to be constructed from the bottom up as a coherent, source-grounded representation. Applied consistently across papers, the same structure connects their research narratives into a global scholarly discourse without discarding local context or provenance. We demonstrate SUDO's capabilities across a comprehensive suite of scholarly knowledge-modeling use cases and performance improvements on a downstream Large Language Model (LLM)-based scientific QA task.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Digital Libraries (cs.DL) |
| Cite as: | arXiv:2610.33018 [cs.CL] |
| (or arXiv:2610.33018v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33018 arXiv-issued DOI via DataCite |
Submission history
From: Pathirage Deelaka Nipun [view email]
[v1]
Thu, 8 Oct 2026 14:09:15 UTC (3,217 KB)
来源：arXiv cs.CL · arxiv.org