Duluth at SemEval-2020 Task 7: Using Surprise as a Key to Unlock Humorous Headlines

Shuning Jin, Yue Yin, XianE Tang, Ted Pedersen


Abstract
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.
Anthology ID:
2020.semeval-1.128
Volume:
Proceedings of the Fourteenth Workshop on Semantic Evaluation
Month:
December
Year:
2020
Address:
Barcelona (online)
Venues:
COLING | SemEval
SIGs:
SIGLEX | SIGSEM
Publisher:
International Committee for Computational Linguistics
Note:
Pages:
986–994
Language:
URL:
https://aclanthology.org/2020.semeval-1.128
DOI:
10.18653/v1/2020.semeval-1.128
Bibkey:
Cite (ACL):
Shuning Jin, Yue Yin, XianE Tang, and Ted Pedersen. 2020. Duluth at SemEval-2020 Task 7: Using Surprise as a Key to Unlock Humorous Headlines. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 986–994, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
Duluth at SemEval-2020 Task 7: Using Surprise as a Key to Unlock Humorous Headlines (Jin et al., SemEval 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2020.semeval-1.128.pdf
Code
 dora-tang/SemEval-2020-Task-7