Abstract This study aims to learn representations of stories in narrative works (i.e., creative works that contain stories) using fixed-length vectors. Vector representations of stories enable us to compare narrative works regardless of their media or formats. To computationally represent stories, we focus on social networks among characters (character networks). We assume that the structural features of the character networks reflect the characteristics of stories. By extending substructure-based graph embedding models, we propose models to learn distributed representations of character networks in stories. The proposed models consist of three parts: (i) discovering substructures of character networks, (ii) embedding each substructure (Char2Vec), and (iii) learning vector representations of each character network (Story2Vec). We find substructures around each character in multiple scales based on proximity between characters. We suppose that a character's substructures signify its ‘social roles’. Subsequently, a Char2Vec model is designed to embed a social role based on co-occurred social roles. Since character networks are dynamic social networks that temporally evolve, we use temporal changes and adjacency of social roles to determine their co-occurrence. Finally, Story2Vec models predict occurrences of social roles in each story for embedding the story. To predict the occurrences, we apply two approaches: (i) considering temporal changes in social roles as with the Char2Vec model and (ii) focusing on the final social roles of each character. We call the embedding model with the first approach ‘flow-oriented Story2Vec.’ This approach can reflect the context and flow of stories if the dynamics of character networks is well understood. Second, based on the final states of social roles, we can emphasize the denouement of stories, which is an overview of the static structure of the character networks. We name this model as ‘denouement-oriented Story2Vec.’ In addition, we suggest ‘unified Story2Vec’ as a combination of these two models. We evaluated the quality of vector representations generated by the proposed embedding models using movies in the real world.

中文翻译：

---

故事嵌入：学习基于角色网络的故事的分布式表示

摘要 本研究旨在使用固定长度的向量学习叙事作品（即包含故事的创意作品）中故事的表示。故事的矢量表示使我们能够比较叙事作品，而不管它们的媒体或格式如何。为了以计算方式表示故事，我们专注于角色之间的社交网络（角色网络）。我们假设人物网络的结构特征反映了故事的特征。通过扩展基于子结构的图嵌入模型，我们提出模型来学习故事中人物网络的分布式表示。所提出的模型由三部分组成：（i）发现字符网络的子结构，（ii）嵌入每个子结构（Char2Vec），以及（iii）学习每个字符网络的向量表示（Story2Vec）。我们根据字符之间的接近度在多个尺度上找到每个字符周围的子结构。我们假设角色的子结构表示其“社会角色”。随后，Char2Vec 模型被设计为嵌入基于共同出现的社会角色的社会角色。由于角色网络是随时间演变的动态社交网络，我们使用时间变化和社会角色的邻接来确定它们的共现。最后，Story2Vec 模型预测每个故事中社会角色的出现以嵌入故事。为了预测事件的发生，我们采用了两种方法：(i) 像 Char2Vec 模型一样考虑社会角色的时间变化，以及 (ii) 关注每个角色的最终社会角色。我们将第一种方法的嵌入模型称为“面向流的 Story2Vec”。'如果很好地理解人物网络的动态，这种方法可以反映故事的背景和流程。其次，基于社会角色的最终状态，我们可以强调故事的结局，这是对人物网络静态结构的概述。我们将此模型命名为“面向结局的 Story2Vec”。此外，我们建议将“统一的 Story2Vec”作为这两种模型的组合。我们使用现实世界中的电影评估了由提议的嵌入模型生成的向量表示的质量。我们建议将“统一的 Story2Vec”作为这两种模型的组合。我们使用现实世界中的电影评估了由提议的嵌入模型生成的向量表示的质量。我们建议将“统一的 Story2Vec”作为这两种模型的组合。我们使用现实世界中的电影评估了由提议的嵌入模型生成的向量表示的质量。