Abstract
In this paper we describe our system submitted to SemEval 2020 Task 7: “Assessing Humor in Edited News Headlines”. We participated in all subtasks, in which the main goal is to predict the mean funniness of the edited headline given the original and the edited headline. Our system involves two similar sub-networks, which generate vector representations for the original and edited headlines respectively. And then we do a subtract operation of the outputs from two sub-networks to predict the funniness of the edited headline.- Anthology ID:
- 2020.semeval-1.129
- 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:
- 995–1000
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.129
- DOI:
- 10.18653/v1/2020.semeval-1.129
- Cite (ACL):
- Tiantian Zhang, Zhixuan Chen, and Man Lan. 2020. ECNU at SemEval-2020 Task 7: Assessing Humor in Edited News Headlines Using BiLSTM with Attention. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 995–1000, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- ECNU at SemEval-2020 Task 7: Assessing Humor in Edited News Headlines Using BiLSTM with Attention (Zhang et al., SemEval 2020)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2020.semeval-1.129.pdf