用用户选定的两篇文档作极点，将文章投射到地球仪上讲故事。
Information Terra: A Narrative-Anchored Semantic-First Projection of Document Embeddings
- 以两篇指定文档为极点，构建语义锚定的地球仪式投影
- 通过密度估计识别主题区域，沿最优路径生成连贯叙事线
- 适合研究长时段事件演变的学者，可直观观察主题与进展
我们提出 Information Terra，一种以叙事为锚的语义优先投影方法。该方法将文档语料库映射到类地球仪的球面上，以用户选定的两篇文档为南北极，其间的大地测量弧线作为本初子午线——纬度表示叙事进展，经度表示主题偏离。通过核密度估计从文档密度中恢复地貌特征，并按主题标注。基于底层叙事一致性图构建的叙事轨迹，在测地线进度上保持单调性，形成可读的故事线。投影轴由用户选定的叙事端点语义锚定，球面隐喻支持旋转与对跖阅读。我们在包含540篇文章的古巴抗议事件语料库上验证了该方法，成功呈现了从奥巴马2016年访问到2021年国际援助期间的叙事演化过程。
原文摘要 · Abstract (English)
We introduce Information Terra, a narrative-anchored semantic-first projection that places a document corpus on an Earth-like globe whose poles are two user-chosen endpoint documents and whose prime meridian is the great-circle geodesic between them on the embedding hypersphere -- so latitude encodes narrative progress and longitude thematic deviation. Land features are recovered from document density via kernel density estimation and labeled by theme. A narrative trail built from the underlying narrative coherence graph, and constrained to be monotone in geodesic progress, provides a readable storyline. The projection's axes are semantically grounded in the user's chosen narrative endpoints, and the globe metaphor affords rotation and antipodal reading. We demonstrate the method on a 540-article Cuban Protests corpus, showing a storyline from Obama's 2016 visit to the 2021 International Aid during the protests.
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。