An Implemented Model of Punning Riddles

In this paper, we discuss a model of simple question–answer punning, implemented in a program, JAE-1, which generates riddles from humour–independent lexical entries. The model uses two main types of structure: schemata, which determine the relationships between key words in a joke, and templates, which produce the surface form of the joke. JAPE-1 succeeds in generating pieces of text that are recognizably jokes, but some of them are not very good jokes. We mention some potential improvements and extensions, including post–production heuristics for ordering the jokes according to quality. Humour and artificial intelligence If a suitable goal for AI research is to get a computer to do “. . . a task which, if done by a human, requires intelligence to perform,” (?), then the production of humorous texts, including jokes and riddles, is a fit topic for AI research. As well as probing some intriguing aspects of the notion of “intelligence”, it has the methodological advantage (unlike, say, computer art) of leading to more directly falsifiable theories: the resulting humorous artefacts can be tested on human subjects. Although no computationally tractable model of humour as a whole has yet been developed (see (?) for a general theory of verbal humour, and (?) for a comprehensive survey), we believe that by tackling a very limited and linguistically-based set of phenomena, it is realistic to start developing a formal symbolic account. One very common form of humour is the questionanswer joke, or riddle. Most of these jokes (e.g. almost a third of the riddles in the Crack-a-Joke Book (?)) are based on some form of pun. For example: What do you use to flatten a ghost? A spirit level. (?) This riddle is of a general sort which is of particular interest for a number of reasons. The linguistics of ∗Thanks are due to Canada Student Loans, the Overseas Research Students Scheme, and the St Andrew’s Society of Washington, DC, for their financial support. Copyright c © 2008, American Association for Artificial Intelligence (www.aaai.org). All rights reserved. riddles has been investigated before (e.g. (?)). Also, there is a large corpus of riddles to examine: books such as (?) record them by the thousand. Finally, riddles exhibit more regular structures and mechanisms than some other forms of humour. We have devised a formal model of the punning mechanisms underlying some subclasses of riddle, and have implemented a computer program which uses these symbolic rules and structures to construct punning riddles from a humour-independent (i.e. linguistically general) lexicon. An informal evaluation of the performance of this program suggests that its output is not significantly worse than that produced by human composers of such riddles.