Computational Modeling of Narrative (Paperback)

The field of narrative (or story) understanding and generation is one of the oldest in natural language processing (NLP) and artificial intelligence (AI), which is hardly surprising, since storytelling is such a fundamental and familiar intellectual and social activity. In recent years, the demands of interactive entertainment and interest in the creation of engaging narratives with life-like characters have provided a fresh impetus to this field. This book provides an overview of the principal problems, approaches, and challenges faced today in modeling the narrative structure of stories. The book introduces classical narratological concepts from literary theory and their mapping to computational approaches. It demonstrates how research in AI and NLP has modeled character goals, causality, and time using formalisms from planning, case-based reasoning, and temporal reasoning, and discusses fundamental limitations in such approaches. It proposes new representations for embedded narratives and fictional entities, for assessing the pace of a narrative, and offers an empirical theory of audience response. These notions are incorporated into an annotation scheme called NarrativeML. The book identifies key issues that need to be addressed, including annotation methods for long literary narratives, the representation of modality and habituality, and characterizing the goals of narrators. It also suggests a future characterized by advanced text mining of narrative structure from large-scale corpora and the development of a variety of useful authoring aids. This is the first book to provide a systematic foundation that integrates together narratology, AI, and computational linguistics. It can serve as a narratology primer for computer scientists and an elucidation of computational narratology for literary theorists. It is written in a highly accessible manner and is intended for use by a broad scientific audience that includes linguists (computational and formal semanticists), AI researchers, cognitive scientists, computer scientists, game developers, and narrative theorists. Table of Contents: List of Figures / List of Tables / Narratological Background / Characters as Intentional Agents / Time / Plot / Summary and Future Directions

敘事（或故事）理解和生成領域是自然語言處理（NLP）和人工智能（AI）中最古老的領域之一，這並不奇怪，因為故事講述是一種基本且熟悉的智力和社交活動。近年來，互動娛樂的需求和對創造具有逼真角色的引人入勝故事的興趣為這一領域提供了新的動力。本書概述了當今在建模故事敘述結構方面所面臨的主要問題、方法和挑戰。本書介紹了從文學理論中引入的經典敘事概念及其與計算方法的映射。它展示了人工智能和自然語言處理研究如何使用計劃、基於案例的推理和時間推理的形式化方法來建模角色目標、因果關係和時間，並討論了這些方法的基本限制。它提出了嵌入式敘事和虛構實體的新表示方法，用於評估故事節奏，並提供了一個觀眾反應的實證理論。這些概念被納入一個名為NarrativeML的註釋方案中。本書確定了需要解決的關鍵問題，包括長篇文學敘述的註釋方法，情態和習慣性的表示，以及敘述者目標的特徵化。它還提出了一個未來的展望，即從大規模語料庫中進行敘事結構的高級文本挖掘，以及開發各種有用的創作輔助工具。這是第一本系統性地將敘事學、人工智能和計算語言學整合在一起的書籍。它可以作為計算機科學家的敘事學入門書，也可以作為文學理論家對計算敘事學的闡釋。本書以非常易於理解的方式撰寫，面向廣泛的科學讀者，包括語言學家（計算和形式語義學家）、人工智能研究人員、認知科學家、計算機科學家、遊戲開發者和敘事理論家。目錄：圖表清單/表格清單/敘事學背景/角色作為有意圖的代理人/時間/情節/總結和未來方向