Automatic Joke Generation: Learning Humor from Examples

Authors: Thomas Winters, Vincent Nys, Daniel De Schreye
Publication Date: 2018-07
Publication Venue: Distributed, Ambient and Pervasive Interactions: Technologies and Contexts
Abstract: Computational humor systems often employ explicit rules encoding assumptions about what constitutes a funny joke. This paper explores how a program can teach itself to generate jokes based on a corpus of rated example jokes. We implement a system called Generalized Analogy Generator (GAG) capable of generating jokes using the "I like my X like I like my Y, Z" template. We use established humor theory and extend computational humor concepts to allow the system to learn the structures of the given jokes and estimate how funny people might find specific instantiations of joke structures. We also implement a platform for the collection of jokes and their ratings, which are used for the training data and evaluation of the system. Since GAG uses generalized components and learns its own schemas, this program successfully generalizes the most well-known analogy generator in the computational humor field.

Citation

APA

Winters, T., Nys, V., & De Schreye, D. (2018). Automatic Joke Generation: Learning Humor from Examples. Distributed, Ambient and Pervasive Interactions: Technologies and Contexts, 10922 LNCS, 360–377.

Harvard

Winters, T., Nys, V. and De Schreye, D. (2018) “Automatic Joke Generation: Learning Humor from Examples,” in Distributed, Ambient and Pervasive Interactions: Technologies and Contexts. Springer International Publishing, pp. 360–377.

Vancouver

Winters T, Nys V, De Schreye D. Automatic Joke Generation: Learning Humor from Examples. In: Distributed, Ambient and Pervasive Interactions: Technologies and Contexts. Springer International Publishing; 2018. p. 360–77.

BibTeX

@inproceedings{winters2018gag,
    issn = {0302-9743},
    abstract = {Computational humor systems often employ explicit rules encoding assumptions about what constitutes a funny joke. This paper explores how a program can teach itself to generate jokes based on a corpus of rated example jokes. We implement a system called Generalized Analogy Generator (GAG) capable of generating jokes using the "I like my X like I like my Y, Z" template. We use established humor theory and extend computational humor concepts to allow the system to learn the structures of the given jokes and estimate how funny people might find specific instantiations of joke structures. We also implement a platform for the collection of jokes and their ratings, which are used for the training data and evaluation of the system. Since GAG uses generalized components and learns its own schemas, this program successfully generalizes the most well-known analogy generator in the computational humor field.},
    journal = {Distributed, Ambient and Pervasive Interactions: Technologies and Contexts},
    booktitle = {Distributed, Ambient and Pervasive Interactions: Technologies and Contexts},
    pages = {360--377},
    volume = {10922 LNCS},
    publisher = {Springer International Publishing},
    isbn = {9783319911304},
    year = {2018},
    title = {Automatic Joke Generation: Learning Humor from Examples},
    language = {eng},
    author = {Winters, Thomas and Nys, Vincent and De Schreye, Danny},
    keywords = {Computational humor},
    organization = {Streitz, Norbert}
}

Related talks

Automatic Joke Generation: Learning Humor from Examples

DAPI18: 6th Conference on Distributed, Ambient and Pervasive Interactions

2018-07-19

Slides

Related project

2017

Solo project

Automatic Joke Generation

My master's thesis about "Automatic joke generation: learning humor from examples"

Back to all publications