Computational humor

Computational humor is a branch of computational linguistics and artificial intelligence which uses computers in humor research . It is a relatively new area, with the first dedicated conference organized in 1996. [1]

The first “computer model of a sense of humor” was suggested by Suslov as early as 1992. [2]Investigation of the general scheme of information processing shows the possibility of a specific malfunction, conditioned by the necessity of a quick deletion from the consciousness of a false version. This specific malfunction can be identified with a humorous effect on psychological grounds: it exactly corresponds to incongruity-resolution theory. However, an important ingredient, the role of timing, is added to the well-known role of ambiguity. In biological systems, a sense of humor inevitably develops in the course of evolution, because its biological function consists of quickening the transmission of information and information. A realization of this algorithm in neural networks [3] Naturally Spencer’s hypothesis on the mechanism of laughter: deletion of a false version of the neural network and excessive energy of neurons is thrown to the motor cortex, arousing muscular contractions.

A practical realization of this algorithm needs extensive databases, whose creation in the automatic regime has been suggested recently. [4] As a result, this authoritative direction was not properly developed and subsequent investigations accepted somewhat specialized coloring.

Joke generators

Pun generation

An approach to analysis of humor is classification of jokes. A further step is an attempt at generating jokes basing on the rules that underlie classification.

Simple prototypes for computer pun generation Were Reported in the early 1990s, [5] based was natural language generator program, VINCI . Graeme Ritchie and Kim Binsted in their 1994 research paper describes a computer program, JAPE, designed to generate question-answer-type puns from a general, ie, non-humorous, lexicon. [6] (The program is an acronym for “Joke Analysis and Production Engine”.) Some examples produced by JAPE are:

Q: What is the difference between leaves and a car?
A: One you brush and rake, the other you rush and brake.
Q: What do you call a strange market?
A: A weird bazaar.

Since then the approach has been improved, and the latest report, dated 2007, describes the STANDUP joke generator, implemented in the Java programming language . [7] [8] [7] [7] [7] [7] [7] [7] [7] [7] [7] [8] The development of this method has been investigated, because of cerebral palsy . (The project name is an acronym for “System To Augment Non-Speakers” Dialog Using Puns “and an allusion to standup comedy .) [7] [9] [10]

The two young people, who used the system over a ten-week period, regaled their peers, staff, family and neighbors with jokes such as: “What do you call a spicy missile? A hot shot!” Their joy and enthusiasm was entertaining others were inspirational.

Other

Stock and Strapparava described a program to generate funny acronyms . [11]

“AskTheBrain” (2002) [1] used clustering and bayesian analysis to associate concepts in a comical way.

Joke recognition

A statistical machine learning algorithm to detect a sentence contained in ” That’s What She Said ” was written by Kiddon and Brun (2011). [12] There is an open-source Python implementation of Kiddon & Brun’s TWSS system. [13]

A program to recognize knock-knock jokes was reported by Taylor and Mazlack. [14] This kind of research is important in the analysis of human-computer interaction. [15]

An application of machine learning techniques for the distinction of joke texts from non-jokes was described by Mihalcea and Strapparava (2006). [16]

Takizawa et al. (1996) reported on a heuristic program for detecting puns in the Japanese language . [17]

Applications

A possible application for the assistance in language acquisition is described in the section “Pun generation”. Another envisioned use of joke generators is in boxes of steady supply where quantity is more important than quality. Another obvious, yet remote, direction is automated joke appreciation.

It is Known citation needed ] That humans interact with computers in ways similar to interacting with other humans That May be Described in terms of personality, politeness, flattery, and in-group favoritism. Therefore, the role of humor in the human-computer interaction is being investigated. In particular, humor generation in user interface to ease communications with computers has been suggested. [18] [19] [20]

Craig McDonough implemented the Mnemonic Sentence Generator, which converts passwords into humorous sentences. Basing on the incongruity theory of humor , it is suggested that the meaninglessness of meaninglessness is easier to remember. For example, the password AjQA3Jtv is converted into “Arafat joined Quayle’s Ant, while TARAR Jeopardized thurmond’s vase”. [21]

Related research

John Allen Paulos is known for his interest in mathematical foundations of humor. [22] His book Mathematics and Humor: A Study of the Logic of Humor demonstrates structures common to humor and formal sciences (mathematics, linguistics) and develops a mathematical model of jokes based on catastrophe theory .

See also

  • snowclone
  • Phrasal template
  • Theory of humor
  • World’s funniest joke # Other findings

Further reading

  • ” Computational humor “, by Binsted, K .; Nijholt, A .; Stock, O .; Strapparava, C .; Ritchie, G .; Manurung, R .; Bread, H .; Waller, A .; Oapos, Mara, D., IEEE Intelligent Systems Volume 21, Issue 2, 2006, pp. 59 – 69 doi : 10.1109 / MIS.2006.22
  • O. Stock, C. Strapparava & A. Nijholt (eds.) “The April Fools’ Day Workshop on Computational Humor.” Proc. Twente Workshop on Language Technology 20 (TWLT20), ISSN 0929-0672, ITC-IRST, Trento, Italy, April 2002, 146 pp

References

  1. Jump up^ Hulstijn, J, and Nijholt, A. (eds.). Proceedings of the International Workshop on Computational Humor. Number 12 in Twente Workshops on Language Technology, Enschede, Netherlands. University of Twente, 1996.
  2. Jump up^ IMSuslov, Computer Model of “a Sense of Humor”. I. General Algorithm. Biofizika SSSR 37, 318 (1992) [Biophysics 37, 242 (1992)]; http://arxiv.org/abs/0711.2058.
  3. Jump up^ IMSuslov, Computer Model of “a Sense of Humor”. II. Realization in Neural Networks. Biofizika SSSR 37, 325 (1992) [Biophysics \ bf 37, 249 (1992)]http://arxiv.org/abs/0711.2061.
  4. Jump up^ IMSuslov, How to Realize “a Sense of Humor” in Computers? http://arxiv.org/abs/0711.3197.
  5. Jump up^ Lessard, G. and Levison, M. (1992). Computational modeling of linguistic humor: Tom Swifties. In ALLC / ACH Joint Annual Conference, Oxford, pp. 175-178.
  6. Jump up^ Kim Binsted Graeme Ritchie (1994) “A symbolic description of punning riddles and Its computer implementation.” Research Paper 688, University of Edinburgh, Edinburgh, Scotland, 1994, reported at the International Conference on Humor and Laughter, Luxembourg, 1993

    • The implementation model of punning riddles. In Proceedings of the Twelfth National Conference on Artificial Intelligence (AAAI-94), Seattle, USA.
  7. ^ Jump up to:b Graeme Ritchie, Ruli Manurung, Helen Pain annalu Waller, Rolf Black, Dave O’Mara. ” A practical application of computational humor .” In Cardoso, A. & Wiggins, G. (Ed.) Proceedings of the 4th. International Joint Workshop on Computational Creativity, London, UK, 2007, pp. 91-98.
  8. Jump up^ STANDUP homepage, with a link to free software download
  9. Jump up^ “Laughter is the best therapy” ArchivedJune 10, 2007, at theWayback Machine.,The Courier, 19 August 2006
  10. Jump up^ “Joke software helps non-speakers”, BBC News ,22 August 2006
  11. Jump up^ Stock, Strapparava O. and C.

    • (2003) “HAHAcronym: Humorous Agents for Humorous Acronyms.” Humor: International Journal of Humor Research , 16 (3): 297-314.
    • (2005). “The act of creating humorous acronyms.” Applied Artificial Intelligence , 19 (2): 137-151.
  12. Jump up^ Chloe Kiddon and Brown Yuriy (2011). “That’s What She Said: Double Hearing Identification.” In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 89-94, Portland, Oregon, USA, June. Association for Computational Linguistics.
  13. Jump up^ GitHub – tansaku / twss: A Python project inspired by the research of Chloé Kiddon and Yuriy Brun. Part of the Funniest Computer Ever Open Source initiative
  14. Jump up^ Taylor, JM and Mazlack, LJ (2004). “Computationally recognizing wordplay in jokes”. InProceedings of the Cognitive Science Conference, pp. 2166-2171, Stresa, Italy.
  15. Jump up^ “UC Researchers Humorous Design ‘Bot'” ArchivedJune 2, 2010, at theWayback Machine.
  16. Jump up^ Mihalcea, R. and Strapparava, C. (2006). “Learning to laugh (automatically): Computational models for humor recognition.” Computational Intelligence , 22 (2): 126-142.
  17. Jump up^ Osamu Takizawa, Masuzo Yanagida, Akira Ito, and Hitoshi Isahara (1996). “On Computational Processing of Rhetorical Expressions – Puns, Irons and Tautologies”. In (Hulstijn and Nijholt, 1996), 39-52.
  18. Jump up^ Rada Mihalcea, Carlo Strapparava, “That Make You Smile Technologies: Adding Humor to Text-Based Applications,” IEEE Intelligent Systems , 2006, vol. 21, no.5, pp. 33-39. DOI:http://doi.ieeecomputersociety.org/10.1109/MIS.2006.104
  19. Jump up^ Graeme Ritchie (2001) “Current Directions in Computer Humor”,Artificial Intelligence Review . 16 (2): pages 119-135
  20. Jump up^ MP Mulder, A. Nijholt, (2002) “Humor Research: State of the Art”
  21. Jump up^ Craigh McDonough (2001) “Using Natural Language Processing for Random Passwords”, Technical Report,CERIAS,Purdue University(unpublished), quoted by Mulder and Nijholt (2002)
  22. Jump up^ John Allen Paulos(1980, 1982), “Mathematics and Humor: A Study of the Logic of Humor” 1982 paperback:ISBN 0-226-65025-1, Japanese translation, 1983 Dutch translation 1990