MARCUS:一种从叙事文本中生成人物弧光的事件中心型NLP流水线
MARCUS: An Event-Centric NLP Pipeline that generates Character Arcs from Narratives
AI总结:
本研究提出事件中心型NLP流水线MARCUS,通过提取叙事中的事件、角色、情绪等建模角色关系并生成图形化人物弧光,在两部奇幻系列作品上验证了方法有效性,为文学理论概念的量化研究及相关应用提供了支撑。
摘要:
人物弧光是文学研究中用于理解人物历程、识别不同文学类型的叙事套路以及确立叙事文本间相似性的重要理论工具。本研究针对从叙事文本中以计算方式生成以事件为中心、基于关系的人物弧光这一全新任务展开研究。为人物弧光提供量化表示能让这一理论概念更具可操作性,并为后续应用铺平道路。我们提出了MARCUS(用于理解故事的弧光建模系统,Modelling Arcs for Understanding Stories),这是一种NLP流水线,可提取事件、参与角色、隐含情绪和情感以建模角色间关系。MARCUS会在整个叙事过程中追踪并汇总这些关系,最终生成以图形化图谱呈现的人物弧光。我们从《哈利·波特》和《指环王》两部长篇奇幻系列作品中生成了人物弧光。我们先对所提方法进行了评估,随后概述了现存挑战,给出了该流水线的应用建议,并对未来工作进行了讨论。
英文摘要:
Character arcs are important theoretical devices employed in literary studies to understand character journeys, identify tropes across literary genres, and establish similarities between narratives. This work addresses the novel task of computationally generating event-centric, relation-based character arcs from narratives. Providing a quantitative representation for arcs brings tangibility to a theoretical concept and paves the way for subsequent applications. We present MARCUS (Modelling Arcs for Understanding Stories), an NLP pipeline that extracts events, participant characters, implied emotion, and sentiment to model inter-character relations. MARCUS tracks and aggregates these relations across the narrative to generate character arcs as graphical plots. We generate character arcs from two extended fantasy series, Harry Potter and Lord of the Rings. We evaluate our approach before outlining existing challenges, suggesting applications of our pipeline, and discussing future work.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。