Abstract
Using a natural language understanding system for commonsense comprehension is getting increasing attention from researchers. Current multi-purpose state-of-the-art models suffer on commonsense validation and explanation tasks. We have adopted one of the state-of-the-art models and proposing a method to boost the performance of the model in commonsense related tasks.- Anthology ID:
- 2020.semeval-1.68
- 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:
- 551–555
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.68
- DOI:
- 10.18653/v1/2020.semeval-1.68
- Cite (ACL):
- Khanddorj Mendbayar and Masaki Aono. 2020. KDE SenseForce at SemEval-2020 Task 4: Exploiting BERT for Commonsense Validation and Explanation. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 551–555, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- KDE SenseForce at SemEval-2020 Task 4: Exploiting BERT for Commonsense Validation and Explanation (Mendbayar & Aono, SemEval 2020)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2020.semeval-1.68.pdf