Duluth at SemEval-2020 Task 7: Using Surprise as a Key to Unlock Humorous Headlines
This work addresses the challenge of humor detection in text for NLP applications, but it is incremental as it applies existing methods to a specific competition task.
The paper tackled the problem of assessing the funniness of edited news headlines by using pretrained transformer-based language models with a contrastive approach inspired by incongruity theory to capture surprise, achieving 0.531 RMSE in Subtask 1 (11th out of 49) and 0.632 accuracy in Subtask 2 (9th out of 32).
We use pretrained transformer-based language models in SemEval-2020 Task 7: Assessing the Funniness of Edited News Headlines. Inspired by the incongruity theory of humor, we use a contrastive approach to capture the surprise in the edited headlines. In the official evaluation, our system gets 0.531 RMSE in Subtask 1, 11th among 49 submissions. In Subtask 2, our system gets 0.632 accuracy, 9th among 32 submissions.