Who's to say what's funny? A computer using Language Models and Deep Learning, That's Who!

TL;DR

This paper explores automatic humor detection and ranking using language models and deep learning, aiming to better understand humor through computational methods.

Contribution

It introduces a language model-based approach for humor detection and discusses future plans to incorporate deep learning techniques.

Findings

Initial results with language models show promise in humor detection.

Framework for ranking humorous statements on a continuous scale.

Plans to enhance methods with deep learning are outlined.

Abstract

Humor is a defining characteristic of human beings. Our goal is to develop methods that automatically detect humorous statements and rank them on a continuous scale. In this paper we report on results using a Language Model approach, and outline our plans for using methods from Deep Learning.