人工智慧一直致力於在複雜系統領域中探索著如何利用電腦進行推理，計畫，學習，以及知識管理，例如如何教一個機器講笑話，這些年同樣吸引著許多研究人員的眼球。由於幽默是一種雙向的交互，人們的理解和表達都會受限於個體的不同而達到不同的效果，但是我們嘗試著在一定的層面上達到產生笑話的效果。我們轉移先前在這個如何讓笑話產生領域的觀點，到我們新的觀點：根據精妙的設計表達我們想要的內容。基於笑話是由一系列的事件組合成的這樣一個觀點，我們建立了一套新的使用增強式學習的方法。根據計算幽默理論中的不和諧理論（Incongruity Theory）和知識本體論語義幽默理論（Ontological semantic theory of humor），我們設定了一個新的可計算獎勵和懲罰的方法來學得一個比較好的政策。

Artificial intelligence pursues reasoning, planning, learning, and utilizing knowledge in a complex domain, such as teaching a machine to tell jokes, which catches many scholars’ eyes for these years. Subjected to the humor as being a double way interaction, both the comprehension and the performance are limited by individuals, though, we attempt to generate a joke in a certain way. We shift a previous vision on how to generate a joke, into a perspective of what to express based on the elaborate layout. Considering that a joke consists of a sequence of events, we set up a new method by using reinforcement learning. Following by the theory of ontological semantic theory of humor (OSTH) and Incongruity Theory, we provide a feasible reward schema to learn a good policy.

[1] Turing, Alan M. "Computing machinery and intelligence." Mind (1950): 433-460.
[2] Binsted, Kim, et al. "Computational humor." Intelligent Systems, IEEE 21.2 (2006): 59-69.
[3] J. Hulstijn, A. Nijholt (Eds.). Automatic Interpretation and Generation of Verbal Humor. Proceedings of the Twelfth Twente Workshop on Language Technology (TWLT 12), joint with 1st International Workshop on Computational Humor (IWCH ’96), 11-14 September 1996 (including pre- and post-workshop activities), ISSN 0929-0672, Enschede, the Netherlands.
[4] Wiseman, R. I. C. H. A. R. D. "Laughlab: The scientific search for the world’s funniest joke." (2002).
[5] Mulder, Matthijs P., and Antinus Nijholt. "Humour Research: State of Art." (2002).
[6] Berlyne, Daniel E. "Humor and its kin." The psychology of humor (1972): 43-60.
[7] Veatch, Thomas C. "A theory of humor." Humor 11 (1998): 161-215.
[8] Rutter, Jason. Stand-up as interaction: Performance and audience in comedy venues. Diss. University of Salford, 1997.
[9] Marteinson, Peter. On the Problem of the Comic. Legas (Ottawa), 2006.
[10] Ritchie, Graeme. "Current directions in computational humour." Artificial Intelligence Review 16.2 (2001): 119-135.
[11] Raskin, Victor. Semantic mechanisms of humor. Vol. 24. Springer, 1985.
[12] Mulder, Matthijs P., and Antinus Nijholt. "Humour Research: State of Art." (2002).
[13] Attardo, Salvatore, and Victor Raskin. "Script theory revis (it) ed: Joke similarity and joke representation model." Humor: International Journal of Humor Research 4.3-4 (1991): 293-347.
[14] Raskin, Victor, and Katrina E. Triezenberg. "Ontological Semantics of Humor: Pre-Conference Tutorial." ISHS-05: The 17th Annual Meeting of the International Society of Humor Studies, Youngstown, Ohio: Youngstown State University. 2005.
[15] Petrenko, Max, and Victor Raskin. "Modeling Abduction within Ontological Semantics." Proceedings of Midwestern Computational Linguistics Colloquium. Vol. 5. 2008.
[16] Taylor, Julia M. "Ontology-based view of natural language meaning: the case of humor detection." Journal of Ambient Intelligence and Humanized Computing 1.3 (2010): 221-234.
[17] Paulos, John Allen. Mathematics and humor: A study of the logic of humor. University of Chicago Press, 2008.
[18] Suls, Jerry M. "A two-stage model for the appreciation of jokes and cartoons: An information-processing analysis." The psychology of humor (1972): 81-100.
[19] Stock, Oliviero. "Creativity and Computational Humor." Computational Humor 2012 (2012): 29.
[20] Sjöbergh, Jonas, and Kenji Araki. "A Complete and Modestly Funny System for Generating and Performing Japanese Stand-Up Comedy." COLING (Posters). 2008.
[21] Labutov, Igor, and Hod Lipson. "Humor as circuits in semantic networks." Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers-Volume 2. Association for Computational Linguistics, 2012.
[22] Binsted, Kim, and Graeme Ritchie. "An implemented model of punning riddles." AAAI. 1994.
[23] Petrovic, Sasa, and David Matthews. "Unsupervised joke generation from big data." ACL (2). 2013.
[24] Kiddon, Chloe, and Yuriy Brun. "That's what she said: double entendre identification." Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers-Volume 2. Association for Computational Linguistics, 2011.
[25] Mihalcea, Rada, and Carlo Strapparava. "Making computers laugh: Investigations in automatic humor recognition." Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2005.
[26] Ritchie, Graeme, et al. "A practical application of computational humour." Proceedings of the 4th International Joint Conference on Computational Creativity. 2007.
[27] Puterman, Martin L. Markov decision processes: discrete stochastic dynamic programming. Vol. 414. John Wiley & Sons, 2009.
[28] Griffin, Z.M., and Ferreira, V.S. (2006) Properties of spoken language production. In M. J. Traxler and M. A. Gernsbacher (eds.) Handbook of Psycholinguistics, 2nd edition. San Diegoo, CA: Academic Press.
[29] Propp, Vladimir. 1968. Morphology of the folk tale [1928]. Bloomington: Indiana University Press.
[30] Taylor, J. M., and V. Raskin. "Natural language cognition of humor by humans and computers: A computational semantic approach." Cognitive Informatics & Cognitive Computing (ICCI* CC), 2013 12th IEEE International Conference on. IEEE, 2013.
[31] Chambers, Nathanael, and Daniel Jurafsky. "Unsupervised Learning of Narrative Event Chains." ACL. 2008.
[32] De Beaugrande, R., & Dressler, W. U. (1981) Introduction to text linguistics / Robert-Alain De Beaugrande, Wolfgang Ulrich Dressler. London ; New York : Longman, 1981.
[33] Watkins, Christopher John Cornish Hellaby. Learning from delayed rewards. Diss. University of Cambridge, 1989.