Neural Joke Generation

Humor generation is a very hard problem in the area of computational humor. In this paper, we present a joke generation model based on neural networks. The model can generate a short joke relevant to the topic that the user specifies. Inspired by the architecture of neural machine translation and neural image captioning, we use an encoder for representing user-provided topic information and an RNN decoder for joke generation. We trained the model by short jokes of Conan O’Brien with the help of POS Tagger. We evaluate the performance of our model by human ratings from five English speakers. In terms of the average score, our model outperforms a probabilistic model that puts words into slots in a fixed-structure sentence.