BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle

TL;DR

BottleHumor leverages the information bottleneck principle to extract relevant multimodal knowledge from vision and language models, enabling unsupervised humor explanation and advancing understanding of humor interpretation in online media.

Contribution

The paper introduces BottleHumor, a novel method that uses the information bottleneck principle to iteratively refine relevant knowledge for humor explanation from multimodal models.

Findings

Outperforms baseline methods on three datasets

Effectively extracts relevant knowledge for humor interpretation

Can be adapted for other knowledge-driven tasks

Abstract

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.