We investigate literary theories of humour from a computational point of view. A corpus of approximately 11,000 jokes is used to train a neural network generating jokes; the state space of such network is then analyzed via appropriate discovery algorithms, and abstractions synthesized by the neural network are compared to those predicted by existing theories.
LOL: An investigation into cybernetic humor, or: Can machines laugh?
BACCIU, DAVIDE;GERVASI, VINCENZO;PRENCIPE, GIUSEPPE
2016-01-01
Abstract
We investigate literary theories of humour from a computational point of view. A corpus of approximately 11,000 jokes is used to train a neural network generating jokes; the state space of such network is then analyzed via appropriate discovery algorithms, and abstractions synthesized by the neural network are compared to those predicted by existing theories.File in questo prodotto:
File | Dimensione | Formato | |
---|---|---|---|
Bacciu_809294.pdf
accesso aperto
Tipologia:
Versione finale editoriale
Licenza:
Creative commons
Dimensione
1.43 MB
Formato
Adobe PDF
|
1.43 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.