Buhscitu at SemEval-2020 Task 7: Assessing Humour in Edited News Headlines Using Hand-Crafted Features and Online Knowledge Bases
Kristian Nørgaard Jensen, Nicolaj Filrup Rasmussen, Thai Wang, Marco Placenti, Barbara Plank
Abstract
This paper describes a system that aims at assessing humour intensity in edited news headlines as part of the 7th task of SemEval-2020 on “Humor, Emphasis and Sentiment”. Various factors need to be accounted for in order to assess the funniness of an edited headline. We propose an architecture that uses hand-crafted features, knowledge bases and a language model to understand humour, and combines them in a regression model. Our system outperforms two baselines. In general, automatic humour assessment remains a difficult task.- Anthology ID:
- 2020.semeval-1.104
- Volume:
- Proceedings of the Fourteenth Workshop on Semantic Evaluation
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona (online)
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- International Committee for Computational Linguistics
- Note:
- Pages:
- 824–832
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.104
- DOI:
- 10.18653/v1/2020.semeval-1.104
- Cite (ACL):
- Kristian Nørgaard Jensen, Nicolaj Filrup Rasmussen, Thai Wang, Marco Placenti, and Barbara Plank. 2020. Buhscitu at SemEval-2020 Task 7: Assessing Humour in Edited News Headlines Using Hand-Crafted Features and Online Knowledge Bases. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 824–832, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- Buhscitu at SemEval-2020 Task 7: Assessing Humour in Edited News Headlines Using Hand-Crafted Features and Online Knowledge Bases (Jensen et al., SemEval 2020)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2020.semeval-1.104.pdf