Abstract
This paper describes our contribution to SemEval-2020 Task 7: Assessing Humor in Edited News Headlines. Here we present a method based on a deep neural network. In recent years, quite some attention has been devoted to humor production and perception. Our team KDEhumor employs recurrent neural network models including Bi-Directional LSTMs (BiLSTMs). Moreover, we utilize the state-of-the-art pre-trained sentence embedding techniques. We analyze the performance of our method and demonstrate the contribution of each component of our architecture.- Anthology ID:
- 2020.semeval-1.107
- Volume:
- Proceedings of the Fourteenth Workshop on Semantic Evaluation
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona (online)
- Editors:
- Aurelie Herbelot, Xiaodan Zhu, Alexis Palmer, Nathan Schneider, Jonathan May, Ekaterina Shutova
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- International Committee for Computational Linguistics
- Note:
- Pages:
- 852–857
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.107
- DOI:
- 10.18653/v1/2020.semeval-1.107
- Cite (ACL):
- Rida Miraj and Masaki Aono. 2020. KDEhumor at SemEval-2020 Task 7: A Neural Network Model for Detecting Funniness in Dataset Humicroedit. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 852–857, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- KDEhumor at SemEval-2020 Task 7: A Neural Network Model for Detecting Funniness in Dataset Humicroedit (Miraj & Aono, SemEval 2020)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2020.semeval-1.107.pdf
- Data
- Humicroedit