LMVE at SemEval-2020 Task 4: Commonsense Validation and Explanation Using Pretraining Language Model
Abstract
This paper introduces our system for commonsense validation and explanation. For Sen-Making task, we use a novel pretraining language model based architecture to pick out one of the two given statements that is againstcommon sense. For Explanation task, we use a hint sentence mechanism to improve the performance greatly. In addition, we propose a subtask level transfer learning to share information between subtasks.- Anthology ID:
- 2020.semeval-1.70
- 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:
- 562–568
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.70
- DOI:
- 10.18653/v1/2020.semeval-1.70
- Cite (ACL):
- Shilei Liu, Yu Guo, BoChao Li, and Feiliang Ren. 2020. LMVE at SemEval-2020 Task 4: Commonsense Validation and Explanation Using Pretraining Language Model. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 562–568, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- LMVE at SemEval-2020 Task 4: Commonsense Validation and Explanation Using Pretraining Language Model (Liu et al., SemEval 2020)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2020.semeval-1.70.pdf