The Construction of a Pun Generator for Language

The Construction of a Pun Generator for Language Skills Development Humor Generation So. Se 2010 Lourdes Lara Tapia

Overview w w w w Introduction. Early pun generators. JAPE. STANDUP in the Praxis. Evaluation Conclusion. References. June 29, 2010 Humor Generation 2

Introduction w What is a Pun Generator? w A pun Generator is a Computer Program which generates jokes. w What is a Joke? w It is a short text which provoke laughter. w A joke has normally a Punchline. w There are different kind of Jokes: w Punning riddles June 29, 2010 Humor Generation 3

Introduction w A punning riddle is a simple question-answer joke in which the answer makes a play on words: w What do you call a good bye that has a tooth? w A saw long. June 29, 2010 Humor Generation 4

Introduction w What kind of ambiguity is used here? Phonetic similarity Semantic relation w What do you call a good bye that has a tooth? Synonym w A saw long. Meronym Homophone w A So long June 29, 2010 Humor Generation 5

Early pun generators w Raskin (1985): w Incongruity Theory. w Lesard & Levison (1992): w VINCI: Tom Swift w “we must hurry”, said Tom Swiftly. w “I hate Math”, Tom added w Binsted & Ritchie (1994): w JAPE: w Punning riddle uses phonological and semantical ambiguity w Used a large lexicon (Word. Net) w Properly controlled evaluation of the output was carried out. June 29, 2010 Humor Generation 6

Early pun generators w Venour (1999): w The Homonym Common Phrase Pun (HCPP). w A one-sentence set-up & w A punning punchline. w Mechanismus are similar to those used in JAPE w Mc. Kay (2002): w WISCRAIC: w Simple puns in 3 -different linguistic forms: w Question-answer, single and two-sentences sequence. w Support 2 nd-language learning June 29, 2010 Humor Generation 7

Early pun generators w Nijholt (2003): w Communication with machines. w Stock et al. (2005): w HAHAcronym: w Acronym funny concepts w Concept funny Acronym w Mihalcea & Strapparava (2006): w Techniques to humor recognition: w Humurous and non-humorous. June 29, 2010 Humor Generation 8

JAPE w Joke Analysis and Production Engine. w What is JAPE? w Computer Program w In Prolog by Binsted in 1994. w Several Version w JAPE-1 (pilot version) & JAPE 2 w JAPE-3 & JAPE-4 (more flexible dictionary module) w STANDUP in 2008. June 29, 2010 Humor Generation 9

JAPE w JAPE produced short texts punning riddles: w What is the difference between a pretty glove and a silent cat? w One is a cute mitten, the other is a mute kitten. w The Jokes were reliably distinguished from Non- Jokes. w The best of these were published in joke books for children. June 29, 2010 Humor Generation 10

JAPE w The three main strategies used to create phonological ambiguity: w syllable substitution, w word substitution & w Metathesis w Joke-construction mechanisms. w Very similar to those in STANDUP June 29, 2010 Humor Generation 11

JAPE w Deficiencies: Few parameters available for variation. There was no way to guide the software. No real user interface. The search for suitable words could be slow, unintelligent and exhaustive. w Good intelligible jokes was very small. w No facilities to compare words for phonological or semantically ambiguity. w w June 29, 2010 Humor Generation 13

STANDUP w System To Augment Non-speakers Dialogue Using Puns. w This Program is aimed at young children, and lets them w w play with words and phrases by building punning riddles through a simple interactive user-interface. Allow young children to explore the language. Children with Complex Communication Needs (CNN). Punning riddle. “Language playground” June 29, 2010 Humor Generation 14

STANDUP Schema Description Rules Templates Phrasal Question or Answer Header Lexical Precondition Header Question Spec. Answer Spec. Preconditions Header Template Spec. Body Keywords June 29, 2010 Humor Generation 15

Fig. http: //www 2. hawaii. edu/~bergen/papers/humor-IEEE. pdf June 29, 2010 Humor Generation 16

STANDUP w What do you call a shout with a window? w A computer scream. June 29, 2010 Humor Generation 17

STANDUP 11 Schema (kind of joke) Header: Description Rules Lexical Precondition: Newelan 2(NP, A, B, Hom. B) Nouncomp(NP, A, B), Homoph(B, Hom. B), Noun(Hom. B) Question Spec. : Answer Spec. : {Shareprop (NP, Hom. B)} {phrase (A, Hom. B)} Templates Header: Shareprop {X, Y} Preconditions: Meronym(X, Mer. X), Syn(Y, Syn. Y) Keywords: Template Spec. : [NP, Hom. B] [mer. Hyp, Mer. X, Syn. Y] June 29, 2010 Humor Generation Phrasal (finish touches) Question (What is the diff…? ) Answer (They’re both…) Header Body 18

STANDUP 11 Schema (kind of joke) Description Rules Templates Header: Lexical Precondition: Header: Newelan 2(NP: computer screen, A: computer, B: screen, Hom. B: scream) Nouncomp(NP, A, B), Homoph(B, Hom. B), Noun(Hom. B) Shareprop {computer screen, scream} Question Spec. : {Shareprop (computer screen, scream)} Preconditions: Answer Spec. : {phrase (computer, scream)} Meronym(computer screen, window), Syn(scream, shout) Keywords: Template Spec. : [NP, Hom. B] [mer. Syn, window, shout] June 29, 2010 Phrasal (finish touches) Question (What is the diff…? ) What do you call a shout with a window? Answer (They’re both…) Humor Generation Header A shout with a window [mer. Syn, window, shout] Body What do you call a NP(shout) with a NP(X, Y) NP(window) 19

STANDUP-Lexicon w Word. Net as JAPE + w Phonetic similarity. w Speech Output. w Picture Support. w Topics. w Familiarity of words. w Vocabulary restriction. June 29, 2010 Humor Generation 21

STANDUP-Facilities w Joke telling: w VOCA: Voice-Output Communication Aid. w assists people who are unable to use natural speech to express their needs and exchange information with other people during a conversation. w User Profiles: w Username. w Two kind of data: w Option settings. w Personal Data. w Standard Package: w Beginner w Touchscreen-user. June 29, 2010 Humor Generation 22

STANDUP-Facilities w Logging: w Logged in a Disc file: w Allows researchers to study usage as required. w Log player w Dump the simulated re-runs into a video file. June 29, 2010 Humor Generation 23

STANDUP-Software w. . STANDUP Simple. bat June 29, 2010 Humor Generation 24

STANDUP-Evaluation w Evaluate the effectiveness of the software. w No ambitious but qualitative study. w A group of 9 children (8 -12 years old) with cerebral palsy. w Scholars used the software spontaneously, w Found the “Tell the jokes-function” amazing and w Re-told the jokes afterwards. w 8 children reacted very positively w 1 of the older boys complained about the quality of the Jokes. w Anecdotal evidence: Children’s communication had improved. June 29, 2010 Humor Generation 25

STANDUP-Evaluation w In the post-testing: w The Preschool and Primary Inventory of Phonological Awareness, PIPA, showed no sign of improved. w Clinical Evaluation of Language Fundamentals, CELF, only the older boy, who complained, showed no sign of improved. June 29, 2010 Humor Generation 26

Conclusion w Humor is one of the most sophisticated forms of human intelligence. w On the cognitive side humor has two very important properties: w it helps getting and keeping people’s attention. w it helps remembering. w On the artificial intelligence side computational humor is a challenge with implications for many classical fields. June 29, 2010 Humor Generation 27

Conclusion w The development of all its facets is not something for the near future, the phenomena are too complex. w Simple puns, at least, can be modelled formally, and can be generated by a program. w The software is definitely usable for a practical application by children with communication disabilities to develop their linguistic skills. June 29, 2010 Humor Generation 28

Discussion w Questions w w Opinion or w w Comments June 29, 2010 Humor Generation 29

Thank you for your attention June 29, 2010 Humor Generation 30

References w w w w w Binsted, K. 1996. Machine humour: An implemented model of puns. Ph. D. thesis, University of Edinburgh, Scotland. Binsted, K. , H. Pain, and G. Ritchie. 1997. Children's evaluation of computer generated punning riddles. Pragmatics and Cognition 5 (2), 305 -354. Manurung, R. , G. Ritchie, H. Pain, A. Waller, D. O'Mara, R. Black (2008). The construction of a pun generator for language skills development. Applied Artificial Intelligence, 22(9) pp. 841 -869. Ritchie, G. 2001. Current directions in computational humour. Artificial Intelligence Review 16 (2), 119 -135. Ritchie, G. 2003. The JAPE riddle generator: technical specification. Informatics Research Report EDI-INF-RR-0158, School of Informatics, University of Edinburgh, Edinburgh. Stock, O. and C. Strapparava. 2003. HAHAcronym: Humorous agents for humorous acronyms. Humor: International Journal of Humor Research 16 (3), 297 -314. http: //www. csd. abdn. ac. uk/~gritchie/ http: //www. csd. abdn. ac. uk/research/standup/software. php http: //www. csd. abdn. ac. uk/research/standup/downloads/User. Manual. html June 29, 2010 Humor Generation 31