Paper: Unsupervised joke generation from big data

ACL ID P13-2041
Title Unsupervised joke generation from big data
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013

Humor generation is a very hard problem. It is difficult to say exactly what makes a joke funny, and solving this problem al- gorithmically is assumed to require deep semantic understanding, as well as cul- tural and other contextual cues. We depart from previous work that tries to model this knowledge using ad-hoc manually created databases and labeled training examples. Instead we present a model that uses large amounts of unannotated data to generate I like my X like I like my Y, Z jokes, where X, Y, and Z are variables to be filled in. This is, to the best of our knowledge, the first fully unsupervised humor generation system. Our model significantly outper- forms a competitive baseline and gener- ates funny jokes 16% of the time, com- pared to 33% for human-generated jokes.