HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge
This work addresses a niche problem in natural language generation for creative language applications, but it is incremental as it builds on existing models and focuses on a specific linguistic phenomenon.
The paper tackled the task of sentence-level hyperbole generation by analyzing syntactic patterns and using commonsense and counterfactual inference, resulting in a method that generates hyperboles with high success rates and intensity scores as shown in evaluations.
A hyperbole is an intentional and creative exaggeration not to be taken literally. Despite its ubiquity in daily life, the computational explorations of hyperboles are scarce. In this paper, we tackle the under-explored and challenging task: sentence-level hyperbole generation. We start with a representative syntactic pattern for intensification and systematically study the semantic (commonsense and counterfactual) relationships between each component in such hyperboles. Next, we leverage the COMeT and reverse COMeT models to do commonsense and counterfactual inference. We then generate multiple hyperbole candidates based on our findings from the pattern, and train neural classifiers to rank and select high-quality hyperboles. Automatic and human evaluations show that our generation method is able to generate hyperboles creatively with high success rate and intensity scores.