Abstract
This paper presents our strategies in SemEval 2020 Task 4: Commonsense Validation and Explanation. We propose a novel way to search for evidence and choose the different large-scale pre-trained models as the backbone for three subtasks. The results show that our evidence-searching approach improves model performance on commonsense explanation task. Our team ranks 2nd in subtask C according to human evaluation score.- Anthology ID:
- 2020.semeval-1.67
- 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:
- 543–550
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.67
- DOI:
- 10.18653/v1/2020.semeval-1.67
- Cite (ACL):
- Jiajing Wan and Xinting Huang. 2020. KaLM at SemEval-2020 Task 4: Knowledge-aware Language Models for Comprehension and Generation. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 543–550, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- KaLM at SemEval-2020 Task 4: Knowledge-aware Language Models for Comprehension and Generation (Wan & Huang, SemEval 2020)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2020.semeval-1.67.pdf
- Code
- huangxt39/KaLM
- Data
- CommonsenseQA