Abstract
This paper deals with computational detection of humor. It assumes that computational humor is an useful task for any number of reasons and in many applications. Besides these applications, it also shows that recognition of humor is a perfect test platform for an advanced level of language understanding by a computer. It discusses the computational linguistic/semantic preconditions for computational humor and an ontological semantic approach to the task of humor detection, based on direct and comprehensive access to meaning rather than on trying to guess it with statistical-cum-syntactical keyword methods. The paper is informed by the experience of designing and implementing a humor detection model, whose decent success rate confirmed some of the assumptions while its flaws made other ideas prominent, including the necessity of full text comprehension. The bulk of the paper explains how the comprehensive meaning access technology makes it possible for unstructured natural language text to be automatically translated into the ontologically defined text meaning representations that can be used then to detect humor in them, if any, automatically. This part is informed by the experience, subsequent to humor detection, of designing, implementing, and testing an ontological semantic text analyzer that takes an English sentence as input and outputs its text meaning representation (TMR). Every procedure mentioned in the paper has either been implemented or proven to be implementable within the approach.
Similar content being viewed by others
Notes
It would be distracting from the immediate goals of this paper to elaborate here on the crucial differences between the ontology described here and designed to represent meaning for computational applications, on the one hand, and the prevalent controlled-vocabulary-type ontologies proliferating recently in the government and industry and designed for human use, on the other (see Obrst (2007) for a good survey of the latter and Hempelmann & Raskin (2008) for the comparison of the semantic ontology to the others).
The shown list has been enriched in the current implementation of OST, but since facets do not contribute much to the joke analysis in this paper, the list is left as it was first introduced.
The detailed TMRs are not shown here, but screen captures of the proprietary software can be available with a signed NDA.
Simple ambiguity should not be confused with script opposition. A related discussion on common puns can be found in Hempelmann 2003.
As pointed out by C.F. Hempelmann 2008, personal communication.
SO setup:punchline was suggested by C.F. Hempelmann 2008, personal communication.
It should be noted that while it may seem that a large amount of common sense reasoning is involved here, all of it is contained in the appropriate ontological concepts. While possibly surprising to mainstream, i.e., non semantical NLP researchers, it is perfectly feasible,, as the practical applications of the technology on other domains reveal.
Notice that A hostess showed (his) seat (to a man) introduces a different meaning: a hostess could point his seat to the man or explain to him where his seat is without walking him there.
In reality, a shortcut is used, and a knowledge base of previously TMR’ed texts is consulted to determine the most suitable property.
No phrasal senses, such as approach-about, qualify here syntactically.
Strictly speaking, this TMR should activate another property speech act and fill it: speech act: interrogative. This property is rarely used in the implementations of OST because most of the expository texts in the applications are monotonously “assertive” on it.
The fillers of the desirability and intentionality are high and medium, which, incidentally, are classical examples of fuzzy sets (Zadeh 1965), memberships of which are expressed with the use of facets.
Property of speech act with the filler “imperative” could be added to TMRs 12, 13 and 14.
Cause here should not be looked as the causal property, but rather the event.
References
Attardo S (1994) Linguistic theories of humor. Mouton de Gruyter, Berlin
Attardo S, Raskin V (1994) Non-literalness and non-bona-fide in language: An approach to formal and computational treatments of humor. Pragmat Cogn 2(1):31–69
Binsted K (1995) Using humour to make natural language interfaces more friendly. Workshop on AI, ALife and Entertainment. In: Int Jt Conf Artif Intell
Binsted K, Bergen B, Coulson S, Nijholt A, Stock O, Strapparava S (2006) Computational humor. In: IEEE Intell Syst (special sub-issue), 21
Deneire M (1995) Humor and foreign language teaching. Humor Int J Humor Res 8(3):285–298
Gruber TR (1993) A translation approach to portable ontology specification. Knowl Acquis 5:199–200
Gruber TR (1995) Toward principles for the design of ontologies used for knowledge sharing. In: Guarino N, Poli R (eds) Special issue: The role of formal ontology in the information technology. Int J Hum Comput Stud 43(5–6):907–928
Hempelmann CF (2003) Paronomasic puns: target recoverability towards automatic generation, Doctoral dissertation, Purdue University
Hempelmann CF (2008) Computational humor: going beyond the pun. In: Raskin V (ed) The primer of humor research. Mouton de Gruyter, Berlin, New York
Hempelmann CF, Raskin V (2008) Semantic search: content versus formalism. In: Proc LangTech
Mihalcea R, Pulman S (2007) Characterizing humour: an exploration of features in humorous texts. In: Proc Conf Comput Linguist Intell Text Process (CICLing), Springer, Mexico City
Mulder MP, Nijholt A (2002) Humour research: state of the art. University of Twente, Enschede
Nijholt A (2002) Embodied agents: a new impetus to humor research. In: Stock O, Strapparava C, Nijholt A (eds), The April Fool’s Day Workshop on Computational Humor
Nirenburg S, Raskin V (2004) Ontological Semantics. MIT Press, Cambridge
Obrst L (2007) Ontology and ontologies: why it and they matter to the intelligence community. In: Proc Second Int Ontol Intell Commun Conf
Raskin V (1985) Semantic mechanisms of humor. Reidel, Dordrecht
Raskin V (1996) Computer implementation of the general theory of verbal humor. In: Proc IWCH, Int Workshop Comput Humour, Enschede
Raskin V (1998) From the editor. Humor: Int J Humor Res, 11 (1), 1–4
Raskin V (2002) Quo Vadis computational humor? In: Stock O, Strapparava C, Nijholt A (eds) The April Fool’s Day Workshop on Computational Humor, 31–46
Reilly M (2007) “Sharing a joke could help man and robot interact.” New Scientist, August
Ritchie G (2001) Current directions in computational humour. Artif Intell Rev 16(2):119–135
Ritchie G, Manurung R, Pain H, Waller A, Black R, O’Mara D (2007) A practical application of computational humour. In: Proc 4th Int Joint Conf Comput Creat, pp 91–98
Savignon SJ (1991) Communicative language teaching: state of the art. TESOL Quart 25(2):261–277
Schank R, Abelson RP (1977) Scripts, plans, goals, and understanding: an inquiry into human knowledge structures, Erlbaum
Stock O (1996) Password swordfish: verbal humour in the interface. In: Proc IWCH, Int Workshop Comput Humour, Enschede
Stock O, Strapparava C (2002) HAHAcronym: humorous agents for humorous acronyms. In: Stock O, Strapparava C, Nijholt A, The April Fools’ Day Workshop on Computational Humor, 125–135
Suls JM (1972) A two-stage model for the appreciation of jokes and cartoons. In: Goldstein PE, McGhee JH (eds) The psychology of humour: theoretical perspectives and empirical issues. Academic Press, New York
Taylor JM (2008) Towards informal computer human communication: detecting humor in a restricted domain, Doctoral dissertation, University of Cincinnati
Taylor JM Mazlack LJ (2007) An investigation into computational recognition of children’s jokes, In: 22nd Conf Artif Intell
Taylor JM, Raskin V (2010) Fuzzy ontology for natural language. Submitted to NAFIPS′10
Taylor JM, Hempelmann CF, Raskin V (2010) On an automatic acquisition toolbox for ontologies and lexicons. In: Proc ICAI′10, Las Vegas
Vega G (1989) Humor competence: the fifth component. Unpublished Masters’ thesis. Purdue University, West Lafayette
Zadeh LA (1965) Fuzzy sets. Inf Control 8(3):338–353
Acknowledgments
The author greatly appreciates Victor Raskin’s comments and suggestions on this work. The ontological semantics research and implementation upon which the joke analysis draws were done in close collaboration with Victor Raskin and Christian Hempelmann as well as with the assistance of the OnSe Group at RiverGlass Inc.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Taylor, J.M. Ontology-based view of natural language meaning: the case of humor detection. J Ambient Intell Human Comput 1, 221–234 (2010). https://doi.org/10.1007/s12652-010-0014-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-010-0014-2