摘要
　　在人工智慧的領域中，自動產生故事是已經發展很久的技術。對於教育及遊戲而言，能夠讓電腦自動地依照需求來產生故事是一件相當具有潛力的事情。例如：現代電腦遊戲的故事情節都很長，而且也包含了不同的角色，這都必須要花費很多人力去產生故事。然而，如果電腦遊戲能夠擁有自動產生故事情節的能力，它能夠更吸引遊戲玩家，也可以減輕開發者在撰寫故事情節的負擔。在教育方面，故事反饋系統可以提供學生即時的反饋，並且建議學生如何寫出更好的故事。儘管已經有很多不同的自動產生故事方法(如：透過語句的文法結構、故事基本架構、智慧型代理人來產生故事)，但是這些方法還是需要大量的人工撰寫故事內容，這對於自動產生故事是相當大的限制。
　　在本篇論文中，我們提出了新的自動產生故事方法，此方法的靈感來自於演化式計算(一種基於達爾文物競天擇說的方法)。演化式計算的目標是透過模仿物競天擇的過程，找出對於一個問題的較佳解法。本系統中的其中一個重要特色為：實現了利用不同產生故事的管道，自動地產生完整故事給使用者。產生故事方法是自動地透過從既有的故事文章中擷取部分內容，將其重新排列組合之後，而產生出新的故事。我們認為可以從大量的故事中找出隱含的背景知識。再利用評分函數，讓系統可以依照不同的挑選準則找出不同的故事背景。在本篇論文，我們專注於三種不同的挑選準則：角色的個性、角色的行為合理性及故事的精采度。

Abstract
A Genetic Algorithm Approach To
Story Generation
Automatic story generation is one of the long standing field of Artificial Intelligence. Having the ability to create stories on demand is a great potential for education and video games. For example, modern computer games contain long story lines and multiple different of characters. This requires enormous amount of work to produce game. However, if computer games have a capability to write its own story line, it can engage the game players even more whilst decreasing the burden of writing game plots from developers. In education, feedback systems can potentially provide students with instant feedback and give suggestions of how to write better stories. Even though several other approaches have been introduced already (e.g., grammar based, schema based and intelligent agents), they tend to rely heavily on handwritten resources. Which brings severe limitations on its scalability.
In this thesis, we proposed a new approach to story generation which takes its inspiration from evolutionary computing that is based on the natural selection theory of Darwin. The goal of evolutionary computing is to imitate the natural selection process that can potentially obtain better solutions to a problem. One of the key features of this system is that it is complete end-to-end, realizing the various components of the generation pipeline heuristically. Generation of stories is leveraged automatically from existing story corpus and reformulated into new short stories to be presented to the user. We think story generation can be a search task, operating over a number of stories that can be generated from knowledge inherent in a corpus. Using scoring functions, the system can search the story space based on different selection criteria. In this thesis we focus on evaluation on three criteria, namely, character balance, character believability and story vividness.

1 Introduction
1.1 Hypothesis ................................... 3
1.2 Contributions.................................. 3
1.3 ThesisOverview ................................ 4
2 Related Work 6
2.1 Storyingredients ................................ 6
2.2 Grammarbased................................. 7
2.3 Schemabased.................................. 9
2.4 Problemsolvingapproach ........................... 11
2.5 Intelligentagent ................................ 11
2.6 Commonsense.................................. 14
2.7 Summary .................................... 14
3 Genetic algorithm based approach 15
3.1 Geneticalgorithm ............................... 15
3.1.1 Initialpopulation............................ 16
3.1.2 Crossover ................................ 17
3.1.3 Mutation ................................ 18
3.1.4 Selection ................................ 19
3.1.5 Fitnessfunctions ............................ 20
3.2 Experiment ................................... 23
3.2.1 Corpus ................................. 23
3.2.2 SearchParameters ........................... 23
3.2.3 Evaluation ............................... 24
3.2.4 Results ................................. 24
3.3 Summary .................................... 26
4 Conclusion and Future works 28
4.1 Conclusion ................................... 28
4.2 Futuredirections ................................ 29

[1] Inderjeet Mani. Computational Modeling of Narrative. 2012.
[2] George Lako. Structural complexity in fairy tales. School of Social Sciences, Uni-
versity of California, Irvine, 1972.
[3] Perry W Thorndyke. Cognitive structures in comprehension and memory of narrative discourse. Cognitive psychology, 9(1):77–110, 1977.
[4] Vladimir Propp. Morphology of the Folktale, volume 9. University of Texas Press,
2010.
[5] Shohei Imabuchi and Takashi Ogata. A story generation system based on propp theory: As a mechanism in an integrated narrative generation system. In Advances in Natural Language Processing, pages 312–321. Springer, 2012.
[6] Ursula Kretschmer, Volker Coors, Ulrike Spierling, Dieter Grasbon, Kerstin Schnei- der, Isabel Rojas, and Rainer Malaka. Meeting the spirit of history. In Proceedings of the 2001 conference on Virtual reality, archeology, and cultural heritage, pages 141–152. ACM, 2001.
[7] Chris Fairclough and P ́adraig Cunningham. A multiplayer case based story engine. Technical report, Trinity College Dublin, Department of Computer Science, 2003.
[8] Seymour Benjamin Chatman. Story and discourse: Narrative structure in fiction and film. Cornell University Press, 1980.
[9] Scott R Turner. Minstrel: a computer model of creativity and storytelling. 1993.
[10] Stuart Russell and Peter Norvig. Artificial intelligence: a modern approach. 1995.
[11] Mari ̈et Theune, Sander Faas, Anton Nijholt, and Dirk Heylen. The virtual story- teller. ACM SigGroup Bulletin, 23(2):20–21, 2002.
[12] Ivo Swartjes and Mari ̈et Theune. A fabula model for emergent narrative. In Technologies for Interactive Digital Storytelling and Entertainment, pages 49–60. Springer, 2006.
[13] IMT Swartjes and Mari ̈et Theune. The virtual storyteller: Story generation by simulation. 2008.
[14] Hugo Liu and Push Singh. Makebelieve: Using commonsense knowledge to generate stories. In AAAI/IAAI, pages 957–958, 2002.
[15] Mitchell Melanie. An introduction to genetic algorithms. Cambridge, Massachusetts London, England, Fifth printing, 3, 1999.
[16] Brad L Miller and David E Goldberg. Genetic algorithms, tournament selection, and the e↵ects of noise. Complex Systems, 9(3):193–212, 1995.
[17] Adam Lipowski and Dorota Lipowska. Roulette-wheel selection via stochastic ac- ceptance. Physica A: Statistical Mechanics and its Applications, 391(6):2193–2196, 2012.
[18] William C Mann and Sandra A Thompson. Rhetorical structure theory: A theory of text organization. University of Southern California, Information Sciences Institute, 1987.
[19] Frank Thomas and Ollie Johnston. Disney animation: The illusion of life. Abbeville Press, 1981.
[20] Jo ̃ao Dias and Ana Paiva. Feeling and reasoning: A computational model for emotional characters. In Progress in artificial intelligence, pages 127–140. Springer, 2005.
[21] Catherine Havasi, Robert Speer, and Jason Alonso. Conceptnet 3: a flexible, mul- tilingual semantic network for common sense knowledge. In Recent advances in natural language processing, pages 27–29. Citeseer, 2007.
[22] Marie Lebert. Project gutenberg (1971-2008), 2008.