BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle
This addresses the challenge of identifying useful knowledge for humor interpretation in online communications, which is incremental as it builds on existing multimodal and knowledge-based approaches.
The paper tackles the problem of interpreting humor in multimodal content by introducing a method that uses the information bottleneck principle to elicit and refine relevant world knowledge from vision and language models for generating humor explanations in an unsupervised manner, achieving advantages over baselines on three datasets.
Humor is prevalent in online communications and it often relies on more than one modality (e.g., cartoons and memes). Interpreting humor in multimodal settings requires drawing on diverse types of knowledge, including metaphorical, sociocultural, and commonsense knowledge. However, identifying the most useful knowledge remains an open question. We introduce \method{}, a method inspired by the information bottleneck principle that elicits relevant world knowledge from vision and language models which is iteratively refined for generating an explanation of the humor in an unsupervised manner. Our experiments on three datasets confirm the advantage of our method over a range of baselines. Our method can further be adapted in the future for additional tasks that can benefit from eliciting and conditioning on relevant world knowledge and open new research avenues in this direction.