中文标题#
通过分层和语义归一化知识图谱的视觉叙事鲁棒符号推理
英文标题#
Robust Symbolic Reasoning for Visual Narratives via Hierarchical and Semantically Normalized Knowledge Graphs
中文摘要#
理解视觉叙事，如漫画，需要结构化的表示，这些表示能够捕捉多个层次的故事组织中的事件、角色及其关系。 然而，符号化叙事图通常存在不一致和冗余的问题，其中相似的动作或事件在不同的注释或上下文中被标记为不同。 这种差异限制了推理和泛化的有效性。 本文介绍了一种用于分层叙事知识图的语义归一化框架。 基于认知基础的叙事理解模型，我们提出了使用词汇相似性和基于嵌入的聚类来整合语义相关的动作和事件的方法。 归一化过程减少了注释噪声，对齐了叙事层次间的符号类别，并保持了可解释性。 我们在 Manga109 数据集中的标注漫画故事上展示了该框架，将归一化应用于面板级、事件级和故事级图。 在叙事推理任务（如动作检索、角色定位和事件总结）上的初步评估表明，语义归一化提高了连贯性和鲁棒性，同时保持了符号透明性。 这些发现表明，归一化是迈向可扩展的、受认知启发的多模态叙事理解图模型的关键步骤。
英文摘要#
Understanding visual narratives such as comics requires structured representations that capture events, characters, and their relations across multiple levels of story organization. However, symbolic narrative graphs often suffer from inconsistency and redundancy, where similar actions or events are labeled differently across annotations or contexts. Such variance limits the effectiveness of reasoning and generalization. This paper introduces a semantic normalization framework for hierarchical narrative knowledge graphs. Building on cognitively grounded models of narrative comprehension, we propose methods that consolidate semantically related actions and events using lexical similarity and embedding-based clustering. The normalization process reduces annotation noise, aligns symbolic categories across narrative levels, and preserves interpretability. We demonstrate the framework on annotated manga stories from the Manga109 dataset, applying normalization to panel-, event-, and story-level graphs. Preliminary evaluations across narrative reasoning tasks, such as action retrieval, character grounding, and event summarization, show that semantic normalization improves coherence and robustness, while maintaining symbolic transparency. These findings suggest that normalization is a key step toward scalable, cognitively inspired graph models for multimodal narrative understanding.
文章页面#
PDF 获取#
抖音扫码查看更多精彩内容