Neural Joking Machine : Humorous image captioning
This addresses the challenge of creating AI-generated humor for applications in entertainment or human-computer interaction, but it is incremental as it builds on existing image captioning methods.
The paper tackles the problem of generating humorous image captions by proposing a system that outputs funny captions using a novel Funny Score for optimization and a self-collected BoketeDB dataset. The result shows the proposed Neural Joking Machine method is verified as effective compared to a baseline CNN+LSTM model and human-created captions.
What is an effective expression that draws laughter from human beings? In the present paper, in order to consider this question from an academic standpoint, we generate an image caption that draws a "laugh" by a computer. A system that outputs funny captions based on the image caption proposed in the computer vision field is constructed. Moreover, we also propose the Funny Score, which flexibly gives weights according to an evaluation database. The Funny Score more effectively brings out "laughter" to optimize a model. In addition, we build a self-collected BoketeDB, which contains a theme (image) and funny caption (text) posted on "Bokete", which is an image Ogiri website. In an experiment, we use BoketeDB to verify the effectiveness of the proposed method by comparing the results obtained using the proposed method and those obtained using MS COCO Pre-trained CNN+LSTM, which is the baseline and idiot created by humans. We refer to the proposed method, which uses the BoketeDB pre-trained model, as the Neural Joking Machine (NJM).